NPCI AI Research Team, Aman Kumar, Asit Desai +15cs.AI cs.CL
Banks need conversational systems that can answer product questions, assist customers with account-related requests, and operate safely within strict operational and regulatory constraints. General-purpose language models do not reliably meet these requirements. They fall short when a task requires grounded information, correct tool use, or cautious handling of bank-specific sensitive situations. We introduce FiMI Banking, a controlled Indian retail-banking setting. We build it from vetted banking documents, structured ground truth, synthetic customer backgrounds, and banking tools. We evaluate two post-training approaches: preference optimization for response-level behavior, and reinforcement learning with verifiable rewards for multi-turn tool-use tasks. Preference optimization improves safe behavior substantially: out-of-scope refusal rises from 52% to 80%. Reinforcement learning improves edge-case performance from 0.509 to 0.718 and order-sensitive task performance from 0.590 to 0.679, while using 29% fewer generated tokens. These results show that preference optimization and verifiable-reward reinforcement learning address complementary requirements for reliable banking agents.
Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM, FEniCS, or COMSOL takes real expertise. Large language model (LLM) agents promise to turn a natural-language request into a working simulation, and recent CAE agents add simulation-specific machinery: multi-agent decomposition, domain retrieval, and scripted reflection. That machinery suited weak base models; modern harnesses already supply multi-turn reasoning, tool use, and execution feedback. We ask what a CAE simulation agent still needs beyond a generic harness. With information access and repair budget held fixed, a single-agent harness matches or beats multi-agent specialized systems (FoamBench 96.4\% vs.\ 88.2\%). Ablations trace this to capabilities the harness already provides: execution-feedback repair lifts FoamBench from 71.8\% with no repair round to 96.4\%, while scripted reflection adds nothing. The one input that still helps is domain knowledge supplied as solver tutorials, our largest measured gain (80.9\% to 96.4\%).
As LLMs increasingly act through tools, they must reconcile user instructions, parametric knowledge, and dynamic environmental observations before taking actions. We introduce KC-Bench, a controlled multi-turn benchmark for measuring this capability across world-knowledge conflicts, input inconsistencies, and multi-source temporal conflicts. Its 238 tasks are manually screened from more than 1,000 generated candidates and combine a user simulator, stateful tools, deterministic environment assertions, an open-source natural-language evaluator, and human trajectory verification. Evaluation of nine models, including DeepSeek-V4-Flash, GLM-5.2, and MiniMax-M3, shows substantial cross-domain variation: no model handles factual correction, identity consistency checking, and temporal conflict resolution reliably across all settings. In the simulated environments, missed conflicts can propagate to tool calls or synthetic protected-data flows. KC-Bench isolates this model-level behavior rather than ranking complete agent frameworks, and provides a reproducible diagnostic for developing conflict-aware reasoning and execution safeguards.
Modern vision-language models (VLMs) can directly answer many image-grounded questions, yet they often struggle with complex queries requiring fine-grained visual details or external knowledge. To acquire this missing evidence, agentic VLMs invoke tools such as image cropping, image search, and text search. However, existing training paradigms primarily evaluate tool-use based on final answer correctness, leaving evidence acquisition and utilization insufficiently supervised. This leads to two critical shortcomings: (i) models frequently issue redundant or off-target tool calls that fail to gather necessary evidence, and (ii) even when appropriate tools are called, models often fail to extract the necessary information from the resulting observations. To address these limitations, we introduce the NTEP (Necessary Tool-Evidence Path), a novel annotation scheme that explicitly specifies the essential external evidence and corresponding tool calls for each query. Building upon this, we propose NTEP-R (NTEP Reward), a supervision mechanism ensuring that each tool invocation strictly advances the reasoning process toward the final solution. Specifically, our approach rewards the agent for aligning its pre-call intent with a necessary evidence-seeking goal, and for ensuring the information summarized from the post-call observation aligns with the necessary evidence. Furthermore, we introduce a non-repeated-goal regularizer to penalize redundant calls that revisit satisfied NTEP goals. Extensive evaluations on seven image-grounded benchmarks demonstrate that our 8B-parameter instantiation, NTEP-8B, significantly improves both search-oriented accuracy and tool-use efficiency within a unified three-tool framework. These results highlight the critical value of fine-grained tool-evidence path supervision for training robust agentic VLMs.
Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty +3cs.AI
We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. The environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text. We use CivBench to characterise agent behaviour across four model families in 23 admissible runs. The sample is a pilot, not a model ranking: aggregate outcomes do not reliably discriminate models at this scale. Instead, we introduce two interface-level metrics that the environment makes measurable: Proactive Monitoring Rate (PMR), capturing whether agents actively query latent strategic state, and RAG@10, capturing whether commitments stated in structured planning reflections are executed within ten subsequent turns. Across runs we observe two consistent patterns under a shared playbook protocol. Agents under-monitor strategically relevant state that is available but requires explicit querying: despite playbook guidance to query victory progress every 20 turns, agents do so only every 30 to 75 turns, and in 7 of 20 detectable defeats they failed to query within the 20 turn warning window before game end. Agents also frequently fail to execute near-term commitments stated in their own planning reflections (RAG@10 between 48.2% and 65.8% across models). Both patterns arise despite tool access and explicit guidance, and we interpret them as deviations under instruction rather than absences of capability. We release the environment, scenarios, logs, metrics, and analysis pipeline at https://github.com/lmwilki/civ6-mcp
Ke Zhang, Yankang Liu, Roya Zandi +1cs.AI cs.MS cs.SE
Scientific benchmarks are commonly built by domain experts who write tasks and cross-check one another's work, or who adapt existing material from textbooks, published papers, and online resources. These routes can produce strong evaluations, but they require substantial per-item labor. Language models can reduce this repeated work by proposing candidates quickly. The remaining problem is acceptance. We target scientific questions whose answers require computations with specialist software rather than unaided reasoning alone. A candidate is invalid if its script fails or returns a different answer, or trivial if a model answers it without the software. We present ToolGate, which treats every generated item as a proposal and keeps it only if three gates pass. First, an executable solution script must reproduce the proposed answer when run with the scientific software. Second, randomized no-tool screening rejects candidates that models can already solve from the prompt alone. Third, a tool-using agent must solve each survivor within a fixed time limit. We instantiate ToolGate in FEniCSx with 500 generation attempts. The local-verification gate retains 478 candidates. For final reporting, we rescreen this pool after generation: two randomized no-tool screens exclude 222 from the reported pool, and direct GPT-5.5 API calls at medium reasoning (the API default) exclude another 121. Of the remaining 135, a GPT-5.5 Codex CLI agent with access to FEniCSx solves 130; exact deduplication leaves 128 unique protocol survivors. ToolGate turns repeated answer checking and difficulty screening into an auditable process while leaving domain design and final review to experts.
Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, existing approaches suffer from two key challenges: brittle multi-step and multi-turn reasoning caused by incompatible tool output types and API schemas, and performance degradation under large tool catalogues. To address these, we introduce \textbf{Tool Primitives}, a design that replaces rigid API schema-based invocation with natural language as the interface for tool calling, where each tool is wrapped with an LLM interface that handles schema resolution and execution internally, enabling natural inter-tool communication for nested and multi-turn tool calling. Building on Tool Primitives, we host \textbf{ToolFace}, a centralized repository of 25,519 functions from which LLMs dynamically retrieve only the relevant tools at inference time, eliminating the need to enumerate raw API schemas in context. To orchestrate Tool Primitives and ToolFace reliably in complex settings, we further propose \textbf{HEART}, a \textbf{H}arness \textbf{E}ngineering framework via \textbf{A}gent-native, \textbf{R}eusable \textbf{T}ool Primitives, comprising a Planner, Router, and Verifier that jointly support dynamic tool invocation planning, multi-step execution, and feedback-driven recovery. Experiments on five benchmarks demonstrate that HEART outperforms SFT-based models by $10\%$ on average and surpasses GPT-5.4, Claude-4.6-Sonnet, and Gemini-3.1-Pro by $6\%$ on average while reducing API cost by up to $85\%$. On 50 real-world tasks, HEART achieves $84\%$ task completion, $3.8\times$ the average of three frontier commercial models ($22\%$).
Training open-ended agents via reinforcement learning (RL) is hindered by the lack of verifiable gold answers and scalable rubrics. Moreover, even near the model's capability boundary, long-horizon open-ended agentic tasks often yield brittle and unstable rewards, resulting in weak or noisy rollout contrast that obscures fine-grained optimization signals for group-based policy learning. To address these challenges, we propose ARISE-RL, a novel full-cycle self-evolution framework that couples a task/rubric Generator and a reasoning Solver through rubric-mediated co-evolution. The Generator grounds tool-related rubric criteria in real tool observations and is rewarded for producing valid, intermediate-difficulty tasks aligned with the Solver's evolving capability boundary. The Solver, in turn, learns from fine-grained rubric satisfaction signals through multi-step reasoning and tool use. We further introduce Reward-Gated Self-Evolution Distillation (RG-SED), which selectively distills a memory-augmented variant of the same policy back into itself only when the memory yields empirical reward improvement, thereby reducing distribution mismatch and avoiding blind imitation of noisy guidance. Finally, to support rigorous evaluation, we present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning. Extensive experiments demonstrate that ARISE-RL consistently achieves robust and stable overall state-of-the-art performance across all evaluated benchmarks.
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.
Long-horizon tool-use agents need not only to search and plan, but also to decide when to finalize. We study late-stage pressure states, in which an agent is biased toward submitting a final answer that appears complete and polished while key constraints remain unresolved. We first train a linear probe to show that this pressure state is identifiable from the agent's hidden states. Then, we use activation interventions along this pressure direction and find that shifting the hidden states changes both the pressure score and whether the agent continues tool use or submits early. Through controlled context manipulations, we further see that the pressure is mitigated by constraint clarity and action mapping. Based on these findings, we propose Probe-Sensed Pressure Relief (PSPR), a plugin that applies lightweight pressure relief direction under moderate pressure and moves to structured organization under high pressure risk. Experiments on multiple long-horizon benchmarks show that our method consistently strengthens existing agent methods.
While reinforcement learning has enabled LLM-based search agents to invoke external tools, existing methods train under fixed budgets and cannot adapt when constraints vary at deployment. We propose AnySearch, a framework that enables a single policy to perform budget-aware search under any budget constraint through a training scaffold and curriculum reinforcement learning. In the first phase, we train the agent with explicit budget state injection and structured reasoning prompts that guide efficient allocation under linearly decaying budgets. In the second phase, the scaffold is removed and the agent learns to operate autonomously under adaptively sampled budget constraints, matching inference conditions. Both phases are optimized with a composite reward that couples answer accuracy with budget efficiency through absolute and relative signals, where an adaptive weight amplifies the efficiency signal for high-accuracy queries and attenuates it for low-accuracy ones. Extensive experiments on seven general and multi-hop QA benchmarks show that our method outperforms baselines across all budget scales, generalizes to unseen constraints beyond the training range, and achieves superior tool productivity without excessive token overhead. Our code is available at https://github.com/xwsun01/AnySearch.
Riccardo Mansutti, Andrea Pomarico, Robert Jakob +3cs.AI eess.SY
Large Language Model (LLM) agents increasingly automate multi-step engineering workflows through tool use, interpretation of intermediate results, and iterative planning. Diagnosing and resolving non-convergent power flow cases is a promising yet largely unexplored application, as it requires engineering judgment, experimentation, and decision-making within constrained action spaces. We introduce a benchmark that evaluates these capabilities across multiple LLMs and three architectures: \emph{chatbot}, \emph{single agent}, and \emph{multi-agent} systems. The evaluation covers two power grids and 46 cases per grid, each requiring one or more corrective actions to restore convergence. The benchmark defines the simulation environment, observation and action spaces, and evaluation metrics, providing a reproducible foundation for developing agentic AI systems for power system planning and operation. The code is available at https://github.com/Mansutti081/RestoreBench
Chemistry questions often demand exact computation and database lookups that a language model cannot supply from its parameters, so it must reach for external tools. Tool use here is a three-part problem: select the right tool from a large pool, fill it with correctly typed arguments, and chain calls so that each consumes the outputs of the last. CheMatAgent, a previously published system, addresses this with hierarchical evolutionary MCTS: separate policy and execution models searching tool-call trees under two learned critics, one regressed partly onto GPT-assigned scores. We show that a single policy suffices. Our model interleaves reasoning, tool calls, and returns in one left-to-right generation, trained by a supervised warm-up and then outcome-level reinforcement learning against a programmatic reward read directly off the gold call chain, which leaves no learned critic and no judge in the training loop. On ChemToolBench multiple-tool comprehensive chemistry, on both backbones CheMatAgent use, we improve Tool F1 by 5.5% and Return F1 by 9.6% on Qwen-2.5-7B, and by 3.7% and 3.9% on Llama-3.1-8B, compared with their strongest search configuration, at one model invocation per question, against a search whose cost grows with the tree; we also lead answer Pass Rate on Qwen-2.5-7B.
AI-generated video detection, which aims to distinguish AI-generated videos from real ones, has recently received increasing research attention. To perform this task reliably, a key challenge lies in accurately identifying subtle-yet-measurable unnatural artifacts. In this work, we address this challenge from a novel perspective of tool-mediated evidence discovery and propose Tool-Using Expert MLLM-based AI-generated Video Detector (TUE-Detector), a novel framework for AI-generated video detection. TUE-Detector trains a general MLLM into a task-tailored tool-using expert detector that learns to invoke suitable tools, collect concrete evidence of unnaturalness, and reason over the evidence for reliable detection. Meanwhile, TUE-Detector further introduces novel designs to equip the expert detector with high-quality and suitable tools. Extensive experiments demonstrate the effectiveness of our framework.
Recent advances in large language models and multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic systems designed to tackle complex, long-horizon RS tasks. However, existing systems often rely on monolithic decision-making frameworks, which fail to accommodate the multi-stage, interdependent nature of RS tasks. This centralized approach leads to challenges such as unstable task execution, incorrect tool usage, and error propagation across stages. To address these issues, we propose HiRS-Agent, a hierarchical multi-agent system for long-horizon RS task solving. HiRS-Agent adopts a two-level collaborative architecture: the Manager Layer handles dynamic routing, step-level verification, replanning, and termination control, while the Specialist Layer organizes domain-specific tools according to the RS workflow and is responsible for subtask reasoning and tool execution. To further enhance the system's capability, we introduce a two-stage supervised tuning strategy and a verification-guided hierarchical reinforcement learning stage to jointly optimize coordination and tool-use policies. Experiments on Earth-Agent Benchmark and ThinkGeo show that HiRS-Agent substantially improves long-horizon tool-use capability and final-task correctness, demonstrating the effectiveness of structured multi-agent collaboration for reliable RS agents. The code is publicly available at https://github.com/IntelliSensing/HiRS-Agent.
Current dialogue systems struggle with dynamic information retrieval, often leading to hallucinations and lower response accuracy. We address this by adapting the ReAct framework for Task-Oriented Dialogue, enabling Large Language Models (LLMs) to access external knowledge and produce factual responses. Mainly, we propose an unsupervised fine-tuning pipeline that harvests reasoning trajectories via in-context learning inference. High-quality samples are filtered using an LLM-based judge to construct a robust training set. This is enhanced by a unsupervised self-improvement loop, where improved checkpoints generate increasingly better trajectories for subsequent fine-tuning iterations. Experiments on the SIMMC dataset demonstrate that ReAct-based systems outperform baselines due to superior reasoning and tool use. Notably, our fine-tuned 8B model surpasses a 70B in-context system. Finally, we present an error analysis, impact of scene complexity, and cross-domain generalization.
Tanzim Ahad, Ismail Hossain, Md Jahangir Alam +3cs.CR cs.AI
The key limitation of current state-of-the-art influence-based guardrails is that they do not reliably distinguish a legitimate, user-authorized action from a malicious, unauthorized action when both rely on external tool information. This ambiguity can cause benign actions to trigger unnecessary verification and intervention, reducing utility and adding latency. We expose this limitation through an authorization-equivalence audit of 96 conditions derived from 24 base cases. Within matched source comparisons, we hold authorization, the exact committed action, and its intended effect fixed, changing only whether a required value comes from the user or a legitimate tool result. Although the action remains unchanged, this harmless relocation shifts the causal signal toward the attack region in all 24 cases under both Llama and Gemma scorers. Matched unauthorized controls show that the signal remains attack-sensitive, yet the benign relocation produces a larger average score shift than the actual change in authorization. Architecture-level evaluation shows how this mismatch propagates through guardrail designs. With a semantic monitor, attack success is 0% and utility is 28%, compared with 16% and 60% without it. A shadow-based guardrail allows every tested harmless run, yet does not reject matched unauthorized actions more often overall: 57.5% of unauthorized runs pass automatically before reaching the later security check, compared with 29.2% of authorized runs. These results show that the studied causal signal reveals what shaped an action without reliably encoding whether the action was authorized, and that reference construction and routing are integral to the effective security decision.
Collaborative conversations frequently contain references whose targets are indirect rather than named: resolving "this looks like the fix discussed yesterday" requires combining conversational context with evidence from the surrounding workspace which is accessible through APIs or user interfaces. We formalize this problem as Conversational Reference Grounding (CoRG): using a given set of tools to resolve a reference in conversation to the unique external item intended by the speaker. CoRG is challenging because it combines lexical, semantic, and temporal cues distributed across the conversation and the external workspace. Agents must translate these heterogeneous signals into effective tool use: formulating strategies, discovering plausible candidates, inspecting their metadata and content, and ruling out close alternatives. We study CoRG through RepoRef, a benchmark of 400 developer-chat segments grounded in GitHub issues, pull requests, and commits across 92 repositories. Unlike single-shot retrieval tasks, RepoRef often requires multi-step tool use. Our results show that CoRG remains challenging for current agents, even the best agent reaches only 67.0% success rate, leaving one third of references unresolved. These findings position CoRG as a concrete benchmark for studying how agents search, inspect, and verify information in realistic multi-tool environments.
Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is insufficient in real-world decision settings such as route planning and fleet dispatch. Individual choices interact through shared constraints and costs, so a feasible solution may still be substantially suboptimal. This raises a harder question: can an agent turn information gathered through tools into a globally optimal decision? We introduce AlgoWorlds, a benchmark that transforms formally specified combinatorial optimization problems into partially observed decision environments with verifiable global optima. Each environment contains a hidden instance observed only through task-specific information tools, after which the agent commits to one structured decision evaluated for feasibility and optimality. AlgoWorlds contains 240 environments covering ten combinatorial optimization families and four workload levels. Family-specific deterministic programs generate the instances, exact algorithms certify their optima and determine workload levels, and two structurally different tool interfaces present each underlying instance. We evaluate seven leading LLMs, including Claude Opus 4.8 and GPT-5.6 Sol. Achieving global optimality remains highly challenging: although leading models produce feasible decisions in most cases, the best-performing model reaches exact optimality in only 38.61% of cases. Even when agents collect sufficient information to reconstruct the hidden instance, most failures end in feasible but suboptimal decisions. The challenge therefore extends beyond information acquisition to information integration, global constraint reasoning, and decision verification. The project homepage is available at https://xzx34.github.io/AlgoWorlds/, and the code is available at https://github.com/xzx34/AlgoWorlds.
Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands of context tokens per session. Existing compression strategies typically allocate retention budgets without accounting for the downstream consequences of removing individual tool outputs. Aggressive compression may therefore trigger costly tool re-invocations that offset the initial savings. We call this the compression--consequence gap. To close it, we propose TRACER, which formulates compression as a sequential per-tool decision problem. A lightweight REINFORCE policy assigns query-conditioned retention ratios using only information available at each compression event. Its consequence-aware objective jointly accounts for task success, total token consumption, and post-compression tool re-invocations. To improve credit assignment, TRACER uses a learned outcome model to compare the predicted consequences of the selected retention ratio with those of fully retaining each tool output. On held-out production queries across three compressor backends, TRACER reduces total token consumption by 29--46% relative to keeping all context while maintaining comparable or higher task success. Compared with a tool-type-conditional static policy, TRACER provides an additional 15--18% of token savings. Interventional rollouts show that the learned per-tool credit scores correlate with measured single-tool consequences. The learned policy also yields positive savings when transferred across agent backbones and compressor architectures, and reduces token consumption by 18--25% on five held-out LOCA-bench environments. These results demonstrate the value of consequence-aware, per-tool context retention for improving the efficiency of long-horizon language agents.
Current large language models (LLMs) increasingly benefit from external tool integration, especially for tasks requiring reliable computation and verification. Motivated by this, we study calculator tool calling for improving mathematical reasoning on the Countdown task. We first analyze reasoning failures and find that calculation errors account for a substantial portion of incorrect responses. We then construct supervised fine-tuning datasets to teach the model useful tool-use patterns and how to interpret returned outputs. Building on this tool-formatted policy, we apply several on-policy reinforcement learning methods, including RLOO, RLOO++, GRPO, and DAPO, using automatically verifiable final-answer rewards. To enable a more reliable evaluation, we construct a fresh 1,024-problem held-out Countdown benchmark with no exact overlap with the training data. Our results show that calculator tool integration consistently improves both SFT and RL baselines, yielding roughly 10 percentage-point gains across pass@k. Among the RL methods, Tool-DAPO achieves the strongest performance, improving pass@1 from 35.8% for Tool-SFT to 66.0%. Further analysis shows that RL encourages more effective tool use even when only final-answer rewards are provided. These findings suggest that tool integration reduces arithmetic and verification errors, while RL increases the probability of correct reasoning traces.
One model passed our fidelity check without ever opening the datasheet. We found it while qualifying models for an internal extraction service: a structured-output constraint had silently disabled tool use, and the model answered anyway, with fabricated source text. Only the per-tool trace exposed it. Fidelity -- whether an extracted value matches the source -- is the standard measure for agentic document extraction, and it scores that run a success. We therefore log every tool call in an agentic benchmark of 25 hand-curated claims over three components, with 12 more on a fourth, 37 in all. From that dispatch record we build two instruments: a rule-based failure-attribution classifier, and a silent-failure detector whose two rules check only which tools were called, never the extracted value. The detector raises no flag on 207 clean fidelity-passing extractions across three model families, and recovers all 50 planted faults that withhold exactly the tools its rules check. The two results are not symmetric: the first bounds the false-positive rate, the second is recall by construction, and detection power against runs that call their tools and still answer wrongly is unmeasured. A second, independent oracle, a causal chamber that tests whether the datasheet's claims hold under physical measurement, is intentionally partial: it confirms only what the apparatus can exercise, a verifiable envelope of 2 of those 37 claims, and we give a taxonomy of why the rest are not physically gradable. Under a controlled perturbation, fidelity passes throughout while the chamber verdict flips exactly at the measurement uncertainty. Across three deployed model stacks (one destabilised by its serving stack, not by any capability gap) the tool layer buys portability and observability rather than accuracy, and earns its premium only once a document outgrows the context window.
Multimodal search agents extend parametric knowledge with newly emerging and long-tail evidence from the open web. Yet many existing agentic search environments often expose retrieved evidence only as text and omit tool-returned images from subsequent context, reducing visually grounded trajectories to text-only reasoning. Long-horizon interaction also compounds tool-call, response-length, timeout, and budget failures, which can discard salvageable trajectories, waste rollout computation, and disturb policy updates. To address these issues, we introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery. Retrieved images receive persistent disk references, allowing the model to inspect, process, and cite them throughout the trajectory. Based on this harness, we develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout. For data construction, a strong MLLM uses WeAgent-Harness to discover, synthesize, and verify MMSearch-style tasks and collect expert trajectories. During post-training, our Failure-Aware GSPO (FA-GSPO) recovers salvageable abnormal rollouts and filters invalid ones to improve bounded multimodal planning and search. We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image, distinguishing image-retrieval failures from visual-perception failures. Evaluation on VisTarget-Bench and seven public benchmarks shows that agentic post-training improves the average score by 19.22 points, enabling our model to outperform similarly sized open-source models and rival models with roughly ten times its parameter count.
LLM agents have become a new class of software user, but every surface they work through was designed for someone else. Pages are built for human eyes, which can skim and ignore; tool schemas for programs, which pay nothing to carry definitions they never call. An agent has neither luxury: it re-reads, and pays again for, everything it is shown on every turn. We present String, an open-source runtime that gives this user an interface of its own and treats the job as an operating-systems problem. Tool knowledge moves out of the agent's context and into a common layer that renders it back one view at a time as Markdown. A single SFMD (String-Flavored Markdown) document declares an application's views, typed actions, navigation, and credentials, and the runtime handles discovery, validation, execution, state, and secrets behind two core verbs: /open to see and /act to do. Web and app turn out to be two renderings of one architecture: an SFMD site serves styled HTML to browsers and the raw document to agents, so one grammar reaches apps, files, shells, and the web, even legacy HTML, with no per-site integration. Views stay partial by design, and the staging is causal: disclosing one tier of detail a single turn too early costs up to 23 accuracy points, while proper staging drops wrong-action selection from 28% to 2%. Privilege follows provenance: a remote page may call HTTP but never the shell, and caller-supplied text never expands a stored secret. On an 87-task benchmark that pairs each task with curated skills, operationalizing those procedures as on-demand String apps yields comparable aggregate success across six models from frontier to small (+1.3pp) while using 33.5% fewer tokens among completed episodes, and the resident interface stays a constant 53 tokens at any catalog size. We report the design, the evaluation, and what three months of production use taught us.
Recent work has shown that reinforcement learning from execution feedback can substantially improve text-to-SQL performance, often enabling smaller models to match or exceed much larger systems. However, most existing approaches treat SQL generation as a single-turn task, limiting the model's ability to recover from errors through iterative refinement. We present ReToolSQL, a two-stage training framework for text-to-SQL that combines (i) a supervised warm-start on rejection-sampled reasoning traces with (ii) agentic reinforcement fine-tuning (RFT) over multi-turn tool-use trajectories. The key insight is that the two stages act on complementary axes, the supervised fine-tuning (SFT) on verified privileged-teacher traces expands the set of solvable questions (raising pass@k coverage on the hardest cases), while RFT converts that expanded capability into higher single-pass accuracy by teaching the model when to verify, what evidence to retrieve, and how to repair faulty SQL from execution feedback. Applied to Gemma 4 instruction-tuned (31B), RFT alone achieves 73.66% execution accuracy (EX) on the BIRD-SQL development benchmark (74.12% EX with self-consistency). Initializing RFT from the SFT checkpoint (SFT$\to$RFT) yields our strongest model at 74.32% EX single-pass and 74.77% EX with self-consistency. At the time of writing, this ranked first on the BIRD single-model development-set leaderboard. The approach uses composite rewards anchored on execution correctness, requires no human annotation beyond the benchmark itself, and operates within a single dense 31B model, showing that a properly designed SFT$\to$RFT pipeline over tool-use trajectories is a practical path toward robust enterprise-grade text-to-SQL.
A language model with access to tools can commit to a final claim unsupported by the evidence it has seen, even when a single available tool call would resolve the uncertainty and its instructions explicitly forbid assumptions and guesses. We separate this failure into two precisely defined quantities: occurrence, how often the model makes an unsupported claim on its own, measured from the visible evidence and final claim without using the hidden correct answer; and conditional repair, how often those same naturally occurring unsupported claims are repaired when the missing evidence is supplied. On one fixed Qwen3-32B setup, 33 of 512 first responses to 256 new prompt templates ended with an unsupported established claim. We replayed each case from an exact copy of the state in which the claim occurred; within each matched replay, the alternative tool responses had the same structure and length and differed only in a one-character response code. Resolving evidence repaired 33 of 33 claims; a matched response carrying no useful information repaired 0 of 33. When the evidence supported the original answer, the model preserved 33 of 33, with no observed harm. In a separate experiment, on 64 cases where evidence was needed, an automatic checking rule added 21 evidence calls, corrected all 10 wrong unsupported claims, preserved the 11 that were correct by accident, and never changed a correct answer into a wrong one. On a fixed Gemma 4 setup using the same sampling settings, the model called the tool in all 512 first responses and never made an unsupported final claim, so conditional repair could not be measured for that setup. These results describe two local fixed model setups on two synthetic task families. They do not show how common this failure is in real-world deployments, nor that it reflects a general mechanism shared across models.
Despite their potential in standardized graph tasks, Large Language Models (LLMs) remain brittle to real-world shifts in node identifiers and task formulation. While deterministic graph tools are invariant to such shifts, extracting topological structures from noisy text is highly fragile for LLMs, which often overfit to surface patterns. Moreover, mitigating these parsing failures via multi-agent systems incurs prohibitive latency. To address this, we propose GRAIN, a single-agent framework optimized via reinforcement learning. GRAIN models reasoning as a semantic parsing and tool-execution pipeline, guided by a Structure Invariance Reward. By validating extracted intermediate graphs against ground-truth topologies, this reward forces the LLM to learn robust text-to-structure mappings rather than memorizing linguistic artifacts. We also introduce GRIT, a benchmark evaluating sensitivity to such linguistic shifts. GRAIN outperforms multi-agent baselines by 16.45\% in accuracy with approximately 24\% lower latency. Furthermore, it demonstrates superior structural generalization, halving the out-of-distribution (OOD) gap of SFT models (from 15.77\% to 7.80\%) and maintaining robustness on large-scale graphs beyond the training distribution.
Large language model agents reason, call tools, and act autonomously over many steps, but their agentic skills-correctly sequencing tools, planning under dependencies, judging untrusted inputs, and grounding generated arguments-are hard to measure with accuracy-only leaderboards. We present BekchiAI, which addresses both sides: a benchmark for measuring agentic skill and a platform for observing and controlling live agents. The BekchiAI-Benchmark, a suite of 13 tool-using ReAct agents across 7 task categories (arithmetic, structured/SQL, security detection, URL grounding, planning, orchestration, and tool-policy), totalling 2,057 deterministic, committed test tasks. Every task is verifier-checkable gold answers are computed by running canonical SQL against a real database, computing the exact schedule of a directed acyclic graph (DAG), or evaluating closed-form lambdas including adversarial security samples paired with deliberately imperfect signature scanners so a score reflects the model's own judgment, not the copying of an oracle. We define a small set of behavioral metrics beyond accuracy-tool-call adherence, URL hallucination and source-match, and per-model token cost and report a four-model comparison (Qwen3.7-Max, gemma-4-31B-it, gemma4:26b, gpt-oss-120b) whose story is in the per-family spread, not the aggregate. The benchmark runs are executed using the provided evaluation scripts. BekchiAI-Platform is a complementary web-based observability and control layer for deployed agents, providing full token and latency telemetry as well as remote run termination. The benchmark, evaluation tools, and platform are publicly released.
Agentic (tool-using) language models are mainly trained on tool-call traces and agent trajectories during post-training. These data provide direct behavioral supervision, but producing them requires task environments, execution, and verification, making broad tool and task coverage expensive. Publicly available skills offer another source of training data: they encode reusable tool semantics and workflows but are typically used only as inference-time context. We introduce Skill Pre-Training (SPT), a mid-training method that applies causal language modeling to SkillCorpus, a collection of public multi-file skill packages, optionally mixed with general data. To preserve relations among files within each package, we also introduce Reference Insert, a reference-aware assembly strategy that places supporting files near their mentions in the primary instruction. Experiments across multiple model scales and post-training recipes show that SPT consistently improves agentic performance over mid-training on general or trajectory data, while largely preserving general performance. Data mixture experiments show additional benefits from combining skill data with general annealing corpora. These results indicate that skill packages are a valuable data source for pre-training agentic language models.
Tool-augmented LLMs must arbitrate between two fallible sources when a tool return conflicts with their parametric memory, yet existing evaluations measure source preference without establishing source correctness. We introduce MemToC, a controlled benchmark for post-tool-return arbitration with executable tools. MemToC comprises 6,504 evaluation episodes constructed from 542 quality-controlled factual questions, independently elicited model-specific closed-book answers, and controlled tool returns of known correctness. These components instantiate four source-correctness cases; tool-error and no-tool conditions are separate controls. Across five open-weight 7-9B models, tool returns strongly dominate elicited closed-book answers. The four instruction-tuned models retain a verified-correct answer against an incorrect tool in only 6.5-17.1% of eligible cases, follow a correct tool in 86.0-93.1%, and repeat the tool return in 78.4-86.0% of cases where both sources are wrong. No cross-model ordering remains stable across three instruction-wording variants with the question and episode content held fixed. We compare prompting with SFT and DPO using chain-level cross-fitting over ToolHop, so questions sharing an underlying fact never straddle training and evaluation. We apply an asymmetric success criterion: correct-answer retention must improve without a detected reduction in correct-tool following. SFT and DPO meet this criterion on the same two of four instruction-tuned backbones. Improvements rarely come cleanly: 19 of 20 tested method-model combinations reduce abstention after tool errors or on unanswerable inputs. Transfer beyond MemToC is positive but partial and depends on the model and presentation frame. Correctness-conditioned arbitration can be improved through fine-tuning, but gains must be evaluated jointly with correct tool use, abstention, and robustness to formulation.