Data-centric agents repeatedly perform a discovery step before planning or execution: identifying the data objects relevant to a task. Yet successful discovery outcomes are typically discarded rather than reused. We introduce persistent discovery context, a lightweight memory layer that stores prior intent-to-object mappings and reuses them to augment future retrieval. Across three structured data environments, persistent discovery context consistently improves retrieval quality over metadata-only search, remains effective with automatically generated memories, and exposes a reproducible interference failure mode. In lexically sparse domains, memory-only retrieval can even outperform metadata-based retrieval. These findings suggest that discovery outcomes constitute a useful form of reusable context for data-centric agents.
As large language models increasingly act through external tools, deciding when to call a tool has become a central problem alongside deciding how to use it. Unnecessary tool calls introduce latency, cost, retrieval noise, and error propagation, while missed calls hurt knowledge-intensive queries or questions requiring up-to-date evidence. Existing methods typically trigger tools from absolute query or generation signals, such as difficulty, confidence, or final task reward, and therefore lack an explicit estimate of the instance-level marginal benefit of tool use. We propose CoBRA, a counterfactual boundary-learning framework for tool-augmented language models. CoBRA first constructs internal and external experts from the same base model, collects paired trajectories, and estimates the reward margin between answering with and without tools. This margin partitions data into internal-favored, external-favored, and ambiguous cases. CoBRA then uses clear-margin samples for Boundary-Aware Cold-Start SFT, followed by MARS-RL with reference-split rollouts and counterfactual marginal advantages to optimize boundary decisions. Experiments with retrieval as the main tool on Qwen3-4B show that CoBRA improves tool-use efficiency and boundary-sensitive answer accuracy while maintaining strong performance on tool-dependent out-of-distribution questions.
Large language model (LLM) agents need durable, faithful memory of everything a user or organization has said and stored, yet most memory systems commit to a single organizing structure (a fact store, a vector index, or a knowledge graph) and inherit its blind spots. We present Agent Zero Memory, a provenance-aware long-term memory system that distils a user's conversations, files, and connected sources into three parallel memory systems, each capturing a different facet of the same history: an episodic Memory Events timeline that makes when and what changed first-class, an associative entity-event knowledge graph that links people and projects across sessions, and a semantic, curated, citation-locked Hierarchical Documentary Memory (HDM) of durable facts. A retrieval turn runs an intent gate (so self-contained turns add no latency), a source router, and three concurrent agentic searches, one per system, each a tool-using loop over hybrid (embedding + lexical) search under agent-controlled filters; their grounded, cited answers are integrated into one answer with a single confidence. We formalize the reading discipline: every learned item is a provenanced item carrying its origin, timestamp, and evidence pointer, and every answer is read under a citation lock, so it may cite only evidence its reader actually opened; fabrication is structurally excluded and the system abstains rather than guesses. On two public benchmarks the system sets a new state of the art: 95.60% on LongMemEval and 93.60% on LoCoMo, improving over the strongest prior systems by +0.73 and +1.10 points. A controlled study across eight backbone LLMs characterizes the accuracy-cost-latency frontier: accuracy varies by only 3.4 points while per-query cost varies by ~30x, with near-state-of-the-art quality at up to 20x lower cost per query, the signature of memory-driven, rather than model-driven, quality.
The rapid expansion of reusable skill repositories makes skill routing a critical capability for large language model (LLM) agents. Existing methods treat routing as task-only semantic matching. However, when users with incompatible constraints issue an identical request, this assumption conflates task relevance with skill suitability: a task-only router can select a semantically plausible skill that is unsuitable for the requesting user. To expose this failure mode, we formulate \textit{personalized skill routing} as profile-conditioned retrieval, in which relevance depends jointly on the task and the user profile. We first introduce a profile-counterfactual benchmark, in which the task is held fixed while changes in the user profile induce changes in the reference skill. We further construct paired counterfactual supervision and propose SkillFeed, a progressive retrieve-and-rerank framework that first establishes task--skill alignment and then learns profile-conditioned discrimination. By retrieving body-level evidence and reranking semantically similar but profile-conflicting candidates, SkillFeed identifies skills that satisfy both task requirements and user constraints. On SkillFeed-Bench, SkillFeed attains 75.1\% top-1 retrieval accuracy, a 23.1-point improvement over the corresponding pretrained routing baseline. Adding profile conditioning yields a 35.1-point gain on queries where user profile changes the reference skill. This contrast shows that user profiles are most consequential precisely when they change skill suitability. Our website is publicly available at http://www.aiskillfeed.com .
Large language model agents are moving beyond conventional retrieval-augmented generation toward direct interaction with external corpora. Direct Corpus Interaction (DCI) keeps the full corpus accessible, yet reachable evidence can remain unusable under finite interaction budgets. Required evidence may fail to surface, a surfaced supporting document may remain unopened, or an opened document may fail to expose its decisive fragment. We call this progressive silent loss Evidence Blindness and quantify it through stage-wise evidence realization. Within the DCI paradigm, raw interaction adds little reusable corpus organization, while dynamic-workspace methods reconstruct a query-conditioned interaction space from each query and trajectory. In both cases, useful structure is recovered largely online. We instead formulate large-scale agentic search as finite-budget navigation over reusable corpus structure. We introduce AtlasNav, a persistent multi-view corpus-navigation framework that retains direct corpus interaction but organizes the corpus once into a Corpus Atlas, allowing each query to navigate adaptively rather than reconstruct shared structure. On BrowseComp-Plus, AtlasNav achieves 92.05% strict accuracy while reducing recorded online inference cost by 30.21% relative to the prior dynamic-workspace state of the art. Under matched budgets, it realizes the complete required evidence earlier and approaches the same model's evidence-supplied empirical reference more rapidly. The same representation principle remains effective under PhantomWiki's distinct corpus organization and controlled 10K-1M scaling, and transfers competitively to heterogeneous enterprise knowledge. These results show that agentic search depends not only on accessible evidence, but also on how the corpus is represented so that limited interaction becomes effective navigation.
Long-term language-model agents accumulate memories across interactions, but their retrievers typically do not accumulate retrieval experience. Semantic retrieval is efficient, but embedding similarity does not always reflect whether a memory contains evidence relevant to the current query. Large language model (LLM) rerankers provide stronger query-conditioned relevance scores, yet stateless reranking repeatedly scores a large candidate pool and discards these scores after each query. We introduce EARM, an experience-amortized reranking framework that treats previously acquired LLM relevance scores as reusable retrieval experience. EARM stores sparse query--memory relevance scores in an online matrix, learns their shared structure through causal matrix completion, and combines a small set of newly observed scores with estimated scores to rerank the remaining candidates. The scoring budget decreases as experience accumulates, changing LLM reranking from a repeated per-query expense into a retrieval capability learned over an agent's lifetime. Experiments on long-term conversational memory show that mixed observed-and-estimated reranking improves answer accuracy over semantic retrieval by up to 6.62% and remains effective when only 17.5% of candidates receive direct LLM relevance scores, thereby substantially reducing the inference overhead of LLM reranking. These results motivate a broader view of agent memory: a long-lived agent should remember not only past content, but also how that content has proved useful for retrieval.
Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite dialogue histories and use the transformed memories as retrieval evidence. Despite the progress in organizing fragmented contexts, two major drawbacks persist: (1) information loss from compression, which discards fine-grained but later useful details, and (2) semantic drift from rewriting, which erodes the original tone and situated context. In this work, we propose a novel Human-profile Enhanced Retrieval Optimization framework for long-term agent memory (HERO). Specifically, HERO converts the dialogue history into a traceable heterogeneous memory graph that preserves raw dialogue text as evidence for reasoning, thereby mitigating information loss. For retrieval, HERO extracts initial anchors from the current query and incorporates human profiles via an iterative graph traversal; these anchors and profiles provide guidance signals that adaptively activate the most informative regions of the graph. Experiments on two benchmark datasets show that HERO outperforms strong baselines on both factual and personalized reasoning, while providing more faithful access to raw dialogue evidence.
Long-horizon agents need memory that identifies relevant experience, resolves revisions, and exposes checkable provenance. We present ECHO (Embodied Context and History Orchestration), an auditable memory architecture and service prototype inspired by episodic encoding, consolidation, contextual reinstatement, reconsolidation, and executive control. This is functional inspiration, not neural equivalence; the empirical analysis focuses on retrieval and context construction. Development runs reach 96.29% Hit@10 and 73.64% turn Recall@5 on 1,536 LoCoMo category 1-4 questions, and 97.60% Hit@10, 88.84% turn Recall@5, and 88.71% session Recall@5 on all 500 LongMemEval-S questions. A five-history BEAM gate fails, and in a separate matched 91-question QA sample Mem0 OSS scores 64.84% versus ECHO's 41.76% (exact McNemar p = 0.00107), with a history-cluster interval crossing zero. A post-hoc audit found source-specific phrases in the query-expansion rules. Although no gold answer field entered the runtime, expansion-enabled retrieval scores are therefore descriptive development measurements, not independent confirmation.
Search Agents face a severe reliability crisis during reinforcement learning (RL) fine-tuning. Heuristic Top-K retrieval often causes critical evidence loss or noise inclusion, while over-confidence induced by progressive RL leads to hallucinated answers and redundant searches. To build highly reliable agents, we introduce Conformal Prediction (CP) and propose Conformalized Agentic Search (CAS). This framework establishes reliability guarantees on both the retrieval and training sides: on the retrieval side, an Adaptive Prediction Set (APS), a specific CP realization, translates statistical coverage into dynamic document truncation to construct prediction sets that are adaptive in size; on the training side, Adaptive Conformal Inference (ACI), a dynamic CP algorithm, dynamically constructs prediction sets with controllable coverage to quantify answer confidence, which is then used to penalize low-confidence trajectories within the Group Relative Policy Optimization (GRPO) objective, ensuring the model learns only from reliable ones. Experiments across single-hop and multi-hop QA datasets demonstrate that our framework significantly improves reasoning accuracy while drastically reducing redundant tool invocations, establishing a highly reliable and efficient agent paradigm. Our code is available at https://github.com/S1llyBird/CAS.
Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence and combine them through voting or weighting. However, this independence assumption often fails in multi-agent settings: memories written by different agents may inherit the same upstream source or shared bias, causing correlated evidence to be repeatedly counted and creating a false majority. We term this failure mode \textit{Memory Correlation Bias}. To address the issue, we propose the \textbf{C}orrelation-\textbf{A}ware \textbf{M}emory \textbf{A}rbitration (CAMA) framework that jointly decouples retrieved memories and recovers missing independent evidence. We model the retrieved memories as query-conditioned evidence groups and combine neural dependency inference with provenance-based symbolic priors to estimate the effective number of independent evidence sources, thereby preventing correlated memories from forming a false majority. Since critical independent evidence may be absent from the initial retrieval set, \textsc{CAMA} further learns a sequential recovery policy that actively retrieves alternative evidence or traces upstream sources before making the final decision, aiming to recover sufficient independent evidence for reliable arbitration while minimizing retrieval cost. Experiments on multiple benchmarks demonstrate the superiority of our method over the state-of-the-art baseline methods, suppressing false majorities induced by correlated memories.
Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structured packages of knowledge. However, existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: \emph{\textbf{When do skills help, why do they work, and where do they fail?}} Through controlled experiments across various benchmarks, agent harnesses and LLMs, we isolate the effects of representation, outcome annotation, retrieval difficulty, and cross-framework robustness of skills. To further answer this question, we design a contrastive study that combines controlled quantitative experiments with paired trajectory analysis. We normalize 8,135 trial records from controlled experiments and retain 238 valid unique labels from 240 open-coded records. We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes: skills work when noisy trajectories become procedural anchors that stabilize execution. Skills improve over Workflow Memory by 6.06 points in matched comparisons. Procedural anchoring accounts for 65.7\% of skill cases, versus 4.5\% for explicit knowledge injection, showing that skills stabilize action rather than inject missing facts. Retrieval is a separate bottleneck: as pools grow from 5 to 100, actual-use precision falls from 29.6\% to 3.3\%. Confusable distractors impair offline identification, yet downstream success remains stable; exact ground-truth invocation is neither sufficient nor necessary. Skills fail under brittle assumptions, incompatible contexts, or insufficient adaptation. These findings move evaluation beyond aggregate success rates and guide reliable self-evolving agents.
Agent-memory systems increasingly buy retrieval quality with structure, transforming raw conversation histories into summaries, embeddings, trees, or knowledge graphs before any question is asked. We ask how much of that benefit comes from the structure itself, rather than from competent retrieval over the raw history. We present ReFind, an agent-controlled search interface that builds no semantic structure at all: it leaves the conversation archive unmodified, indexes it lexically at turn granularity, and combines a generic iterative keyword-search loop with four chat-native controls grounded in empirical refinding work: session-aware rank fusion, local context expansion, temporal narrowing, and skipping already-inspected sessions. A separate reasoning stage answers from the collected evidence. Across a broad suite of conversational-memory tasks (single- and multi-hop QA, event ordering, and fact consolidation), roughly 2,800 questions on precise-retrieval and fact-tracking capabilities evaluated under the incremental multi-turn setting of MemoryAgentBench, ReFind attains the highest mean accuracy (58.2) of any system compared, above the strongest graph- and tree-based memory systems (HippoRAG 2, 53.2), all under a GPT-4o-mini backbone matched to every reused baseline. Controlled comparisons to single-shot BM25, a matched generic-agentic BM25 control, component removals, and agentic dense/hybrid variants separately support the roles of agent control, chat-native controls, and lexical retrieval. On LongMemEval-S/M, the same interface reaches 93.2 +/- 3.3 and 89.3 +/- 6.0 with GPT-5-mini. The results indicate that for precise, evidence-grounded questions over chat archives, much of the benefit credited to elaborate memory structures is recoverable by giving an agent controllable search over the unmodified record, with no LLM-based index construction at all.
Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment state have changed. We identify this post-retrieval reuse step as a distinct bottleneck for long-horizon trajectory memory and formulate an evaluation framework that holds candidate retrieval, target state, model, decoding, and tool budget fixed while varying the support delivered to the agent. We instantiate the framework with query-conditioned reuse (QCR), a deliberately simple target-bound note that records a reusable procedure, bindings to recover, applicability conditions, and verification requirements. QCR serves to test the reuse hypothesis rather than to claim a universally preferred memory format. Across 2,391 target instances in WebArena, WorkArena, and AppWorld, QCR reaches 62.3% average Success, 10.7 points above Full Trajectory, while using 48.9% fewer online tokens. Summary reranking selects a reusable memory for 94.8% of targets, placing end-task Success within 1.8 points of an oracle reusable selector. Analyses by trajectory length and source--target binding shift show that direct trajectory injection loses much of its utility as traces grow longer or source-specific values change, whereas target-bound support preserves a larger share of the measured gain. The resulting framework separates retrieval quality from the problem of turning retrieved experience into safe, useful support for a new task.
Ankita Rajaram Naik, Anupama Murthi, Benjamin Elder +6cs.AI
Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\textbf{V}aluating \textbf{A}PI and \textbf{K}nowledge \textbf{R}etrieval \textbf{A}gents), a benchmark of over $8{,}000$ executable APIs across $62$ domains with tasks spanning three settings of increasing difficulty: diverse API interaction styles, multi-hop reasoning over structured APIs, and multi-source reasoning with natural-language tool-use policy constraints. Correctness is verified by re-executing predicted tool calls against live APIs, accommodating multiple valid paths. Using a fixed ReAct harness to isolate model capabilities from agent architecture, we evaluate frontier and open-weight models and find that even the best model achieves only 70.4\% on single-hop endpoint-style tasks and drops to 50--51\% on compositional APIs; performance degrades by over 50\% as reasoning depth increases, and policy-constrained questions expose severe failures (as low as 2.4\% on unanswerable queries). Trace analysis shows failures concentrate at language-mediated reasoning - entity disambiguation, cross-source grounding, rather than tool invocation mechanics. Code is available https://github.com/IBM/VAKRA. Dataset is available https://huggingface.co/datasets/ibm-research/VAKRA
We present SuperLocalMemory 4.0, a governed, local-first memory operating system for AI agents, unifying multi-channel retrieval under reciprocal-rank fusion, bi-temporal recall, multi-scope isolation, role-based access, verified erasure, and a hash-chained audit trail. A reliability spine governs the primary write path: generation-fenced admission, verifiable memory transactions with per-projection apply, verify, compensate and erase owners, and hash-checkable completion manifests. Eleven fault-injection scenarios, each repeated 200 times, upheld 2,199 of 2,200 scoped component properties. This version leads with a negative result. Ten mechanisms here were implemented, reachable on a live call path, and ineffective at their final connection. Implemented, reachable and effective are three different questions, and the third requires an oracle independent of the mechanism under test. We contribute two mechanical invariants that supply one: a prior-distance assertion over Bayesian learners, and a join-liveness assertion over schema-guarded paths that reports where a guard's missing data resides. A three-arm ablation varying only the recall session-identifier namespace moves no posterior with the defect present and every instantiated arm with it absent, while a negative control that writes every ticket but supplies no engagement settles nothing. We withdraw the previous version's governed write-envelope overhead figure: the two paths it differenced are not comparable. Timing the envelope in place gives an 11.0 ms governed write of which the envelope is 70.6 percent, but the generation fence costs 1.9 microseconds and the obligation ledger 42 microseconds. The cost is durability, not governance.
Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, stale memories can remain retrievable and pollute the prompt. We characterize this failure mode as memory pollution: degradation caused by active memories that newer conflicting evidence has superseded. We introduce TEPA, a revocable evidence-memory mechanism that makes validity an explicit state of memory. TEPA represents observations as keyed precedents and revokes active precedents when fresh evidence contradicts them under the same key, allowing retrieval to draw from current evidence while preserving revoked history for audit. Across controlled hidden-regime drift, real file-backed executable drift, and preference-update streams, revocation prevents stale active memory from remaining in the retrieval set after reversal. In controlled drift over 50 seeds, append-only and last-write-wins memory fell below no memory during full reversal (append-only and last-write-wins both 0.210, no memory 0.309, TEPA 0.950), and the same pattern reproduced under real file execution (append-only 0.203, no memory 0.298, TEPA 0.950). On clean MemoryAgentBench SH-6k, TEPA matches a strong last-write-wins cache, confirming that current-key replacement is the decisive operation for single-hop fact consolidation. Boundary tests on multi-hop and very long-context MemoryAgentBench settings expose retrieval-chain and context-selection bottlenecks beyond fact-level validity tracking. Together, these results establish lifecycle revocation as a core memory operation for agents that must falsify, audit, and later re-promote evolving knowledge.
Ao Ding, Hongzong LI, Shiqin Tang +4cs.AI cs.IR cs.LG
Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience. Yet memory evolution is not simply a process of storing more information: new experiences may reinforce, revise, or interfere with existing memory states. Existing systems mainly emphasize memory construction and relevance-based retrieval, but several memories may remain simultaneously relevant while differing in state, temporal validity, or authority. We introduce Controlled Memory Interference (CMI), a controlled diagnostic and data-generation framework for studying how agent memory evolves under different memory relationships. Across controlled memory evolution, benign accumulation has limited effects, whereas relationship-specific interference sharply suppresses update plasticity with little stability gain, either by blocking target-memory exposure or by disrupting its downstream use. Lexical and Dense retrieval exhibit distinct interference pathways, while poisoning is more sensitive to update-authority cues than to recency alone. Beyond diagnosis, CMI provides targeted examples for interference-aware memory learning, improving the distinction between valid updates and interference-inducing memories while preserving performance on original memory tasks. These findings show that memory evolution is shaped not only by memory scale, but also by interactions among accumulated experiences. More broadly, memory interference emerges as an important factor for reliable continual agent memory systems.
Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typically process heterogeneous dialogue content through a uniform summarization and retrieval pipeline, leading to either excessive token consumption or irreversible loss of fine-grained evidence. We argue that historical dialogue content should be handled differently according to its compressibility, temporal dynamics, and fidelity requirements. Based on this insight, we propose LeanMem, a lightweight long-term memory framework. LeanMem first filters out low-value content, then stores informative segments as compact profile memory, temporally structured event memory, or source-grounded record memory, depending on the nature of the information. During maintenance, only dynamically evolving event memories are selectively updated, avoiding redundant consolidation of stable profiles and immutable records. During inference, LeanMem dynamically selects memory types and allocates retrieval budgets according to query-specific evidence demands, assembling relevant evidence on demand. On LoCoMo and LongMemEval-S with GPT-4.1-mini and Qwen3-8B, LeanMem improves accuracy over the strongest memory-based baseline in every setting, by up to 15.1 points, at the lowest or near-lowest construction cost, inference tokens, and latency. The code and datasets are included in the supplementary materials.
The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse information across interactions. Existing memory systems either compress and structure histories for efficient access or perform deep research over broader trajectories. The former lowers online cost but may omit temporal, causal, or cross-step dependencies, while the latter improves evidence coverage at substantial latency and inference cost. This raises a key question: can a memory system achieve strong answer quality while maintaining low online latency? We introduce Router-Mem, an evidence-conditioned progressive execution framework for long-horizon agent memory. Router-Mem first applies a shared low-cost retrieval prefix to obtain evidence. A lightweight sufficiency router then predicts whether the context supports early termination, which enable a single-token decision at inference time. It is trained with evidence-level supervision and rationale-conditioned representation distillation. When evidence is insufficient, Router-Mem reuses retrieval hits to expand memory blocks and perform deeper analysis and aggregation. Experiments on AMA-Bench and BEAM show that Router-Mem achieves 55.17\% and 38.77\% score while reducing average inference time by 27.3\% and 25.5\% compared with full memory execution.
The effective use of search engines by large language models (LLMs) remains a significant challenge, particularly in complex, multi-hop question-answering (MHQA) tasks. These tasks require the model to decompose questions into subqueries, retrieve relevant information, and synthesize answers from multiple sources, often leading to cascading errors due to poor retrieval in early stages. Reinforcement learning (RL) has shown promise in improving LLMs' search capabilities, but it often suffers from sparse rewards during training, hindering the model's ability to learn effectively. To address these challenges, we introduce Guided Retrieval Training (GRT), a novel method that improves the performance of a search agent by restricting the retrieval process during RL training using ground truth information. By focusing on a curated set of relevant documents, GRT provides the model with a stronger learning signal, mitigating the problem of sparse rewards and improving its ability to generate accurate subqueries and synthesize correct answers. Our experimental results demonstrate that GRT achieves consistent performance improvements over existing methods, such as Search-R1, across a wide range of question-answering (QA) tasks. Notably, GRT excels in MHQA tasks, achieving over 40% improvements in performance. Additionally, GRT enhances training efficiency by achieving better QA performance with fewer training steps.
LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged details can obscure the original evidence. We ask whether structured memory access requires generation at all. Zero-Mem introduces \emph{zero-token memory operations}: no step outside final question answering invokes an LLM or consumes LLM input or output tokens; encoder computation is accounted for separately. Zero-Mem preserves original interaction traces as its source of record. It organizes the traces in two complementary ways. An entity--context graph exposes connections across interactions, while a temporal hierarchy preserves conversational locality and session state. For each query, Zero-Mem weighs the two views, retrieves from both, and follows their structure to recover supporting relations or surrounding context. Deterministic calibration first discards conflicting evidence and then keeps the reader's answer grounded in the retrieved traces. Only the final-QA reader invokes an LLM. Across long-memory and long-context question-answering benchmarks, Zero-Mem achieves competitive performance while eliminating LLM calls and LLM-token consumption from memory operations. With the same final-QA reader and context budget, it reduces memory-operation time cost by 57.6\% relative to the fastest compared baseline. Ablations support the contribution of the two views and their query-dependent coordination. Overall, the results show that structured agent memory need not generate an intermediate representation of the past. After peer review, the code and implementation details will be available at \textcolor{blue}{https://github.com/TheMoon0815/Zero-mem}.
Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions using final-answer rewards. Current studies mainly improve training with denser or more structured credit signals, but rarely examine whether retrieval is properly formulated at the policy-environment interface. We observe pronounced retrieval aliasing during Search-R1 training: rollouts for the same question continue to generate distinct query strings, yet their accumulated evidence sets increasingly overlap. We call this phenomenon retrieval-equivalence collapse; in this regime, trajectories approach utility equivalence with respect to retrieval decisions, leaving within-group returns with little effective retrieval contrast. To address this problem, we propose Harness-G, a graph-structured retrieval framework that redesigns this interface. It reformulates free-form query generation as finite action selection: the policy selects an evidence sentence or entity, or chooses to answer, while the environment constructs the menu, tracks retrieval state, and validates and executes each choice. This interface reduces linguistic aliasing and makes same-state alternatives directly comparable. Building on this interface, we introduce Structured Non-myopic Credit (SNC), which uses a frozen answer scorer to compare the selected action with its alternatives and assigns downstream gains to the earlier actions that enabled them. Across six QA benchmarks, Harness-G achieves the highest average F1 at both evaluated model scales, outperforming the strongest baseline, Graph-R1, by 10.74 points at 1.5B and 3.98 points at 3B.
Agent-memory workloads mix direct factual lookup, relation-chain and current-state reasoning, and broad synthesis over long histories. We describe Supra Cognitive Modes (SCM), an architecture that maps explicit or automatically selected per-query modes to retrieval and synthesis payloads over one shared ingest substrate. A frozen semantic classifier and runtime gates dispatch queries among fused lexical and dense lookup, graph or iterative multi-hop handling, and stratified long-form synthesis. The substrate combines multi-granularity embeddings, extracted triples, fact-version metadata, and optional asynchronous enrichments. We characterize the deployed configuration on three benchmarks: Long-term Conversational Memory (LoCoMo; n = 1,986), MemoryAgentBench (MAB; n = 3,671), and LongMemEval (n = 500). The reference run records 84.87% on LoCoMo factoid categories and 68.61% on adversarial abstention, 61.49% on MAB across two repetitions, and 86.00% on LongMemEval. A repository-backed reproduction produces similar aggregate scores and supports task- and mode-conditioned failure analysis. Raw baseline outputs, aligned end-to-end timing for LoCoMo and LongMemEval, and complete token ledgers are unavailable; stored rows also omit some final runtime decisions. The results characterize one implemented routed configuration and its diagnostic failure patterns, while source inspection verifies the per-query control interface and shared-substrate design. Causal routing effects, efficiency gains, and statistical significance remain outside the available evidence.
Maksim Sheverev, David Finkelstein, Sergey Nikolenkocs.LG cs.AI
Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers. We introduce two full-text scientific-memory benchmarks, Public AI Memory (PAIM; 81 papers, 66 questions) and Public Transformers (PTr; 252 papers, 98 questions). We evaluate eight memory/retrieval systems, including our own proposed Theoria, plus a no-retrieval baseline. Our results show that memory leaderboards are not interpretable without the full protocol: ingestion granularity, raw-text preservation, retrieval budget, retrieval modality, rubric audit, and judge choice all affect the outcome. For example, on PAIM Graphiti wins convincingly but uses 2.6M characters of retrieved context per query, and after controlling for retrieval budget the lead disappears. On PTr, for the systems where BM25 retrieval can be added cleanly, the sparse-dense hybrid is the single most significant intervention: hybrid variants of Simple RAG, Mem0, and Theoria tie for the lead within 0.03 points. Multi-judge and human side-by-side calibration show that LLM-as-a-judge rankings are consistent across frontier judges and agree with human evaluation, with an effective resolution of roughly one point on a ten-point scale. We argue that scientific memory should be evaluated as budgeted, modality-aware context restoration rather than as an unconstrained architecture leaderboard, and we release the datasets, harness, raw outputs, judgments, and scripts to reproduce our results and serve as tools for such evaluation. Our code is available at http://gitlab.com/quantellence/research/scientific-recall-bench , and the datasets are available at http://huggingface.co/datasets/quantellence/srb-data .
Long-term memory enables LLM agents to leverage past interactions, but dialogue histories quickly exceed the context window, forcing agents to retrieve relevant subsets at query time. Because useful evidence is sparse and scattered across verbose conversations, retrieval faces a fundamental tension: broadening recall improves coverage but floods downstream reasoning with noise, while compressing memories at write time eases retrieval but irreversibly discards details that future queries may need. We introduce LazyMem, which resolves this tension by deferring all memory construction to query time. Given a retrieved candidate pool, a lightweight model processes it in overlapping parallel windows, selectively retaining and compressing only query-relevant content. The model is trained with supervised fine-tuning followed by reinforcement learning, using a reward that jointly encourages the identification of relevant messages and the generation of compressions that are faithful to the source and useful for answering the query. On LongMemEval, LazyMem-4B achieves an LLM-judge accuracy of 0.85, outperforming the strongest non-oracle baseline while using only 213 answer-context memory tokens, 21.0 times fewer than the baseline. It further generalizes to LoCoMo without target-domain training and reduces mean latency relative to the prior query-time baseline. Code is available at https://github.com/allacnobug/LazyMem.
LLM agents increasingly rely on tool calling to act on external systems, and the Model Context Protocol (MCP) has quickly become its de facto interface. Operating MCP at cloud scale, however, becomes difficult. On the tool provider side, legacy services are not directly callable through MCP; the rapid protocol development also creates ongoing compatibility cost. On the agent side, the number of accessible tool is limited by the LLM context window and inference overhead; mounting a large tool set increases token usage and inference latency and can reduce task success rate. Moreover, for stateful MCP backends with multiple replicas, preserving session affinity increases client-side complexity. We present a cloud-scale gateway system for MCP service. It breaks the direct-connect model on the data plane and offloads legacy service integration, consolidating incompatible MCP variants, access control, tool recommendation, and session-aware routing to the gateway. Hybrid retrieval sustains 98% Top-15 recall; it scales agent tool access to 3,000+ with high tool selection accuracy, and reduces tool selection time by $8.9\times$ and token usage by $23.8\times$, with low per-call overhead, stable under scale-out. Finally, we share the lessons learned from deploying the gateway system in production.
For fifty years, data systems have answered two questions. The relational model asked which records match a predicate; the vector model asked which vectors lie nearest a query. Neither was built for cue-driven, provenance-weighted recall across long sessions. We propose treating long-term agent memory as a distinct data model -- with its own write semantics (encoding, separation, consolidation, provenance) and read semantics (cue-driven activation across a linked memory graph) -- and present FluctlightDB, an embedded engine that implements this contract via experience() and activate(). We make that case carefully, not categorically: we do not claim novelty over Mem0, Zep, or HippoRAG-style memory layers, only an embedded engine contract beneath them. On LoCoMo (official evidence-recall metric; 10 conversations, 1,982 gold spans), CHORUS recalls 99.0% on an internally reproduced July 2026 run. On LongMemEval-S (500 questions, official session_recall@8), our retrieval harness scores 97.6% (488/500); end-to-end QA with our reader/judge stack scores 97.4% (487/500) -- these layers use different protocols than vendor leaderboard figures we cite for context only. On BEIR SciFact (shared MiniLM embeddings, same harness, Recall Fabric on), CHORUS/PRISM edges Chroma on nDCG@10 (0.646 vs. 0.645) and Recall@10 (0.792 vs. 0.783). We also report a small author-designed regression suite (FAMB; paraphrase n=10, other sub-tests n=1) at 100% macro -- internal validation, not peer benchmark. Strangers can verify the engine in under a minute via pip install "fluctlightdb[native]" and a minimal connect() -> experience() -> activate() script (compiled wheel, not source-only). Harnesses and frozen JSON are MIT-licensed. We claim no new neuroscience and no new transformer; we propose a missing layer of the data stack and release an engine others can reproduce and contest.
Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn. We study the regime where memory moves inside the loop, read and written on every step. The obstacle has always been latency: networked stores answer in tens to hundreds of milliseconds, and in-loop retrieval can inflate end-to-end latency by up to 83x when retrieval is expensive. Prior work manages that cost rather than questioning it: serving-layer scheduling hides it, "memory-first" designs ration retrieval to once per turn. We argue latency is a property of where the store lives, not the in-loop pattern: an in-process store answers in ~100us, three orders of magnitude below the network regime, and at that speed the per-step tax collapses. By the extended-mind thesis's parity principle, a store fast enough to be constantly and directly available becomes extended working memory, not a tool the agent merely consults. The premise is causal: holding a fixed per-turn memory-latency budget and varying only the store's answer speed, redundant actions rise monotonically with latency - 0.0 of 12 at in-process speed, 7.2 of 12 at a 110ms cloud round trip (gpt-5-nano, gpt-5-mini; exact permutation p=0.0079). We demonstrate the regime end-to-end: across four GPT-5-class models under a bounded window, recall improves from 0/5 to 3.6-4.8/5 with in-loop memory, store ops at p50 80-165us - though an instructed restate-every-reply baseline also solves it perfectly, at a token cost that grows with the working set. The store never lost a fact in any run (244 of 244 writes kept); every miss traces to the agent's read policy, not the store. Our measurements also relocate the bottleneck: the dominant per-step cost is embedding (~200-400ms over the network); pairing the in-process store with a small local embedder returns the complete operation to a measured ~40us.
Long-lived AI agents require continuity across interactions, but continuity cannot be obtained by simply extending the prompt window. An agent must preserve useful prior experience, retrieve it selectively, distinguish personal context from external evidence, and revise memory when the underlying situation changes. We propose an architectural memory substrate organized along two orthogonal axes: a representational axis spanning structured records, vector representations, and graph relations; and a temporal axis spanning short-term traces, medium-term abstractions, and long-term semantic commitments. Its key design constraint is synchronized structured-vector-graph memory: structured records govern eligibility, vector representations support recall, and graph relations adjudicate support, contradiction, and supersession before gated context projection. Its central claim is that reliable personalization is a memory design problem: useful memory is structured, selectively exposed, continuously consolidated, and epistemically labeled rather than stored as undifferentiated conversation history. Beyond the framework, we instantiate MRMS as a lightweight prototype implementing structured records, vector retrieval, temporal policies, and graph-based revision. The prototype exercises the core substrate mechanisms through pre-generation memory selection, revision, boundary enforcement, and evidence attribution under controlled long-lived interaction scenarios with explicit evidence requirements.
LLM agents increasingly answer questions against knowledge bases they help maintain. A common intuition holds that progressive disclosure, a compact catalog plus a one-line summary per page so the agent loads only what it needs, should make this cheaper than consulting a large monolithic index. We test that on a real 709-page markdown wiki maintained by an LLM. We retrofit it for progressive disclosure and run a preregistered ablation in which four versions of the corpus differ only in how the agent reaches the content: page bodies are byte-identical across arms, frozen as immutable git tags, so any measured difference is due to access structure alone. We cross the arms with three access conditions (a protocol-constrained agent, a free self-routing agent, and a catalog-preload regime) and grade answers blind against verified gold references with a cross-family judge. A pilot upended the premise: a capable tool-using agent never loads the index, inferring a page's path from the question and reading it directly, so the specific saving the retrofit targets does not materialize. We therefore made answer quality primary and cost secondary. Quality is non-inferior (the retrieval arm matches the index baseline within the preregistered margin) while cost falls in every regime, from about a third for a self-routing agent to well over half under catalog-preload, all confidence intervals excluding zero. The saving comes not from avoiding the index load but from more targeted access: the retrieval arm cites fewer pages and takes fewer tool turns. The study doubles as a case study in evaluation validity, applying threat-to-validity discipline to the tooling that produced it.