Shubham Gandhi, Saurabh Goyal, Kiran Kate +1cs.AI cs.LG cs.SE
Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a reward; they are scored once per trajectory, but a single scalar is a poor signal across tens of steps. We propose DRACO: Distributing Rubric-based Advantage for Credit Optimization. It generates rubrics dynamically during training to track the policy's evolving capability, scores those rubrics once per completed trajectory, and redistributes that judgment over the steps responsible for annotated rubrics to produce differentiated per-step advantages in GRPO. The redistribution is closed-form and does not introduce any trained attribution module. On AppWorld, DRACO gains 15.9 points over the base model and 5.3 points over GRPO trained with a sparse ground-truth reward, despite not using any verifiers itself. On out-of-domain Tau-Bench, it gains 5.3 points over the base model even without a frontier judge, beating both ground-truth-reward training and other rubric-based training settings. The code for DRACO is available at https://github.com/IBM/draco.
Graph-based policy optimization improves credit assignment for long-horizon LLM agents by organizing rollout trajectories into state-transition graphs. However, existing methods construct graphs independently within each policy update, discarding transitions discovered by earlier policies and limiting advantage estimation to small, batch-local rollout groups. We propose \emph{Temporal Instance-Graph Policy Optimization} (TIGPO), which extends graph-based credit assignment across policy updates. TIGPO maintains a persistent transition graph for each task, allowing valid transitions discovered by different policy versions to jointly determine credit for current rollouts. To actively reconnect current exploration with historical experience, TIGPO allocates a fixed rollout budget between Exploration slots for ordinary task sampling and Revisit slots for delayed reattempts of previously explored tasks. For each revisit, TIGPO pairs the current rollout group with its corresponding earlier Exploration group to construct a cross-temporal reference. The enlarged reference is designed to stabilize relative advantage estimation under small rollout groups, while comparison on the same task directly captures policy improvement across training stages. Historical transitions and scores serve only as structural and detached statistical references and are never replayed in the policy loss. Experiments on ALFWorld and WebShop demonstrate that TIGPO consistently outperforms prior group-based and graph-based policy optimization methods.
Planning is a central capability that enables agents to decompose complex long-horizon tasks into manageable steps. Test-time search and training-based methods improve planning but incur high inference costs or require expensive training data. Self-evolving memory instead accumulates reusable experience from agent interaction outcomes into an external memory bank, so planning capability keeps improving at inference time without parameter updates. However, existing self-evolving memory methods share an inherent credit assignment problem: they rely on final task outcomes as feedback, but such outcomes conflate plan quality with execution errors and environmental factors, so the accumulated planning experience is often biased and noisy. To address this problem, we propose Credit-Aware Hierarchical Memory Evolution (CHIME), a self-evolving memory framework that maintains a separate planning bank and execution bank and follows an attribute-before-memorize principle: CHIME first attributes each task outcome to the plan, the execution, both, or neither, and then updates only the corresponding memory bank. Extensive experiments on four long-horizon agent benchmarks show that CHIME consistently outperforms state-of-the-art training-based and self-evolving memory baselines. Further analyses reveal several interesting findings. For example, CHIME accumulates effective memory with far fewer items. In addition, the learned memory values faithfully reflect downstream utility: high-quality planning memories are more valuable than execution memories. Finally, the accumulated memory effectively transfers across backbone models. Code will be released at https://github.com/ATH-MaaS/Marco-DeepResearch.
Reinforcement learning (RL) for search agents typically relies on outcome rewards. However, it often fails to achieve effective credit assignment, due to the unclear value of intermediate steps. It is hard to separate their contributions from the final result. In this paper, we propose a dense process supervision method based on fact utility estimation, which models the reasoning process as the accumulation of discrete evidence facts. We first extract structured facts from raw observations and organize them into an explicit fact store. To support credit assignment, we then cluster semantically equivalent facts and infer the posterior utility of each fact cluster using Bayesian estimation over group rollouts. Finally, we convert the estimated fact utilities into dense step-level rewards to guide RL training. Experiments on seven single-hop and multi-hop QA benchmarks show that our method consistently outperforms existing baselines. Ablation studies validate clear relative improvements on multi-hop QA compared to outcome reward-only training.
Self-evolving agents advance toward autonomy by optimizing their harness---prompts, skills, tools, and execution logic---based on environmental feedback. This paradigm, however, is hampered by three challenges: \textit{credit assignment failure}, where terminal success/failure feedback makes it ambiguous which step caused the error; \textit{shortcut learning}, where agents memorize task-specific patterns rather than acquire generalizable capabilities; and \textit{catastrophic forgetting}, where unguarded updates degrade previously acquired competence. In this paper, we introduce HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable agent self-evolution. HarnessEvolve decouples the execution agent from the evolutionary pipeline, assigning execution, evaluation, optimization, and gating to independent agent modules, enabling generalizable and stable harness improvements. Specifically, HarnessEvolve overcomes credit assignment failure by generating reference trajectories (execution paths produced when given the ground-truth answers) and aligning failed executions against them to extract error signals, which are clustered to reveal systematic failure patterns. To prevent shortcut learning and catastrophic forgetting, candidate harness updates must pass two gates: a quality gate that filters data leakage and prompt bloat, and a performance gate that accepts each update if it improves on the current batch without degrading recent batches, with epoch-end validation on a held-out set selecting the best-performing accepted agent snapshot. We conduct extensive experiments on several benchmarks spanning open-domain and enterprise scenarios, using different models and agent frameworks. Results demonstrate that HarnessEvolve consistently outperforms state-of-the-art baselines across all benchmarks and settings, confirming reliability across task domains.
Memory operations of long-horizon LLM agents are hard to supervise: an operation's value is unobservable when it is taken. But they are special -- they leave machine-readable evidence in the trajectory: retrieval hits and answer-time citations. Hindsight Memory-PRM exploits this audit trail twice: offline to train an operation-conditioned memory-utility critic, and online, where retrievals, citations, and one controlled deletion-and-reanswer per probe settle an intervention-calibrated entry-level presence credit, propagated along version chains as an action-level proxy reward -- no per-operation human labels, no Monte-Carlo replay of continuations. On held-out LoCoMo a local 8B policy reaches 77.5% under a fixed shared reader, surpassing its API teacher (65.1%) and all reproduced external systems, at one eighth the context of Mem0's official operating point; on LongMemEval, 79.0%. Ablations attribute the gain to causal calibration rather than signal density, and the policy converges to a multi-version memory organization whose gains no tested open-loop baseline reproduces.
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.
Trajectory-level credit assignment can localize which module of a tool-using LLM agent causes failures using only verifiable signals. We ask whether such failure credit should route a fixed zeroth-order/evolution-strategies (ZO/ES) perturbation budget. Across a synthetic environment and frozen Qwen2.5-1.5B/3B and SmolLM2-1.7B agents, three task families, six allocation schemes, a credit-noise sweep, paired seeds, and exact sign-flip tests, we find no statistically detectable improvement over uniform allocation in any on-pool comparison (no gain of at least 2 percentage points). The joint soft-plus-sigma scheme is equivalent to uniform within a +/- 0.02 AUC margin on 1.5B and 3B; concentrating the full budget on the credit argmax is marginally equivalent on 1.5B, where that module is the verified bottleneck, and significantly worse on 3B. Inverse-propensity debiasing does not rescue routing, and misrouting costs up to -0.074 AUC in-house and -0.118 end-to-end on the BFCL-derived family. Across six fixed-step schedules, loss is linear in bottleneck starvation rate (R^2 = 0.94, descriptive), and a preregistered credit-free coverage floor removes detected harm. Matched-budget burst and step-compensating catch-up schedules are consistent with harm arising from insufficient cumulative parameter movement rather than update frequency. Our primary estimand is optimization efficiency on a fixed task pool. On unseen BFCL functions, the study's one exception is that soft routing exceeds uniform on held-out endpoints (+0.047, p = 0.031, n = 6). A plausible but untested reading is that routing-favored caller improvements transfer while uniform's on-pool gains reflect a synthesizer behavior specific to our harness. We report this exception explicitly and document three failure modes that can silently invalidate ZO/ES experiments on frozen LLMs.
Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over time rather than being fully specified at the initial prompt. Service agents make this challenge especially concrete: users may clarify or revise their goals, while tool responses provide information needed for subsequent decisions. Thus, a final reward alone cannot indicate which actions contributed to resolving the task. Recent methods rely on comparative evidence from other trajectories or resampled continuations, or on separately constructed step-level learning signals, to refine credit. However, a completed rollout already records how information and errors flow between agent actions. We introduce Influence-Aware Policy Optimization (IAPO), which represents each rollout as a typed influence-dependency graph over trainable agent actions, with user and tool observations serving as evidence. IAPO converts support-use and failed-use structure into routing weights that redistribute the same trajectory-level advantage. Experiments with Qwen3-4B and Qwen3-8B demonstrate superior performance over multi-turn reinforcement learning (RL) baselines across three service-agent benchmarks: {τ^2}-Bench, UserBench, and AgentChangeBench. BFCL-v4 Multi-Turn further shows that these gains do not compromise multi-turn function-calling performance. This work advances the understanding of credit assignment in multi-turn user interactions and provides a principled approach to training service agents from sparse outcome feedback.
Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has become the dominant paradigm for enabling this capability. However, existing approaches typically assign uniform trajectory-level advantages and treat all correct tool calls equally, ignoring the varying difficulty and learning value across trajectories and reasoning steps. This can lead to imprecise learning signals that do not adequately distinguish between trivial and challenging tool-use patterns. To address this limitation, we propose HiDiffTIR, a Hierarchical Difficulty-aware policy optimization framework for multi-turn TIR. HiDiffTIR performs difficulty-aware credit assignment at both trajectory and turn levels, enabling the policy to focus on more informative trajectories and harder reasoning steps. Notably, this fine-grained optimization is achieved without additional supervision, relying solely on group-level statistics derived from standard RL rollouts. Extensive experiments on three tool-using benchmarks demonstrate that HiDiffTIR consistently improves multi-turn TIR performance and tool invocation accuracy over strong RL baselines, highlighting the necessity of difficulty-aware credit assignment for effective policy optimization in tool-integrated LLM agents.
Bo Qian, Yuting Wu, Shuang Zeng +3cs.LG cs.AI cs.CL
Credit assignment is challenging in long-horizon agentic reinforcement learning, where supervision often comes only from final rewards. Existing methods refine trajectory-level signals into step-level credits through step grouping or graph-based advantage estimation, but can overlook meaningful intermediate milestones. We propose MileGPO (Milestone Inference with Local Evidence for Graph-Based Policy Optimization), which derives process-level credit from grouped on-policy rollouts through three designs. Milestone Discovery identifies candidate milestones on successful rollouts and recurring traps on failed ones. Reliability-Calibrated Shaping (RCS) weights these candidates by outcome-based confidence, strengthening reliable milestones and traps while down-weighting uncertain ones. Progress-Contrastive Calibration (PCC) further tests whether a candidate reflects local progress and whether its incoming ansition outperforms observed alternatives from the same state.MileGPO requires neither auxiliary models nor additional environment interaction. Experiments on ALFWorld and WebShop show state-of-the-art performance and a small in-distribution to out-of-distribution gap on ALFWorld. Ablations and credit diagnostics indicate that reliability weighting, local progress, and same-state branch evidence complement milestone discovery and resolve ambiguous intermediate credit.
Audited against causal ground truth from executed replay in a single-agent tool environment (ALFWorld), none of the step-level credit signals used to train LLM agents -- LLM-judge scores, outcome-conditioned logprob ratios, or the policy's own confidence -- identifies which steps causally matter better than chance. Existing evaluations grade these signals against annotated step *correctness*; we audit them against step *contribution* -- what re-sampling the policy's own alternatives at each decision point and rolling forward actually changes about the outcome -- and the two come apart. The ground truth itself is structured: causal contribution is sparse (30.5% of decision points where ground truth is defined carry measurable effect), and measurability is model-dependent -- the fraction of points with no policy-supported counterfactual differs by a factor of two (13.1% vs. 26.8%) between two similar-scale policies. The failure mode is identifiable: implicit credit echoes the policy's fluency (median rank correlation +0.75, replicating at +0.70 in a second family under a corrected instrument), while conditioning on the outcome adds no causal information (partial correlation -0.004, Qwen). A confidence-only router recovers pivotal steps at chance level, but cuts judge cost by 13.1% per turn (14.0% per trajectory). In a seven-arm pre-registered training experiment, no arm reliably outperforms the untrained policy, and the checkpoints' apparent instrument signature is fully explained by training dose -- sparser credit retains fewer examples, an order-of-magnitude spread in optimizer steps -- not credit content. Comparisons of credit rules must therefore match effective sample size, or they measure dose, not credit.
Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, while public libraries now hold thousands of them. Which skill to read has thus become a decision the policy itself makes in the middle of an episode, yet no existing signal trains it. We show that the default remedy, outcome-rewarded RL over the candidate slate, cannot teach it, for a structural reason we identify and name selector credit starvation: under a broadcast, sequence-level advantage, the few tokens that name the chosen skill carry a vanishing share of the loss, and the credit they inherit is increasingly wrong-signed as trajectories lengthen. A correct choice is punished whenever the execution after it fails, even though the choice itself is among the most valuable decisions in the trajectory. Auditing a completed run's own training artifacts confirms all three properties, each worsening monotonically with horizon. SkillGate removes the failure by construction: it partitions the token support into two disjoint credit channels, outcome credit reaching only execution tokens, and a separate action-local advantage reaching exactly the skill-naming tokens, positive only when a trajectory's single read is the correct one. On five agentic benchmarks under a 16-candidate slate, SkillGate lifts a 9B policy from 40.8% to 53.2% trial success, well ahead of the identical budget spent on outcome reward alone, while cutting exposure to misleading candidates by two thirds and reading fewer skills.
Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, and conduct iterative search beyond single-turn settings. Yet multi-turn RL training remains highly unstable, often causing severe performance degradation as the number of turns increases. Through theoretical analysis, we identify three tightly coupled sources of instability: rollout-training context mismatch, weak turn-level credit assignment under sparse terminal rewards, and asynchronous policy drift when short and long trajectories are optimized under different policy versions. We show that these issues share a common structural origin in flattened trajectory optimization and address them through a unified reverse-turn formulation. We propose Reverse-Turn Policy Optimization (RTPO), which organizes multi-turn rollouts as sparse reverse trees and performs turn-level policy updates in temporal reverse order, aligning each decision with its downstream continuation. RTPO enables causally consistent turn-level credit assignment and on-policy continuation to control asynchronous drift. We provide theoretical guarantees showing that RTPO eliminates context mismatch and asynchronous drift under the proposed turn-level formulation, reduces credit bias, and converges to recursive optimality. Experiments on multi-turn agentic RL benchmarks show that RTPO improves upon trajectory- and turn-level baselines by 21.50% and 10.76%, respectively, highlighting its potential to support more stable training for tool-using agents.
Agent evaluations and trace-based learning often compare outputs across transformed views through a post-response correspondence treated as neutral preprocessing. We show that this correspondence is a measurement intervention: omitting it can manufacture sensitivity, an over-aggressive map can manufacture invariance, and multiple optimal correspondences can leave mechanism labels and signed learning credit unidentified. We develop a validity theory and audit with three components: two-sided validation of nuisance removal and response preservation, all-optima identification of downstream conclusions, and uncertainty propagation after validity is established. We characterize the linear feasibility boundary for response-preserving nuisance removal, compute sharp ranges over exact-optimum correspondence sets, and give a distribution-free certificate that retains a credit coordinate only when all exact optima agree on its nonzero sign. Across public code and SQL pipelines, two deterministic optimal tracebacks disagree on temporal localization for 55.9% of 1,586 nonzero trajectory pairs; two frozen 800-rollout tool-use audits, including a task-and-seed-disjoint replication, expose exact-optimum reversals of intended turn-level credit, although a clean public quick-start subset shows none. A pre-registered transport gate failed on natural responses; frozen corrected and held-out controls then show that a map calibrated only on benign examples erases every retained harmful response, while two-sided validation selects response-preserving alternatives. Cross-view correspondence must therefore be declared, validated, and propagated into uncertainty before agent evaluation or credit assignment supports a point conclusion.
User-facing tool agents must coordinate dialogue and tool use as user goals unfold over multiple turns. Yet interactive reinforcement learning typically reduces each rollout to a terminal reward, assigning the same credit to effective elicitation, errors, and later repair. The next user turn is more than context: it also provides noisy, temporally local evidence about the preceding user-to-user segment. We introduce \textbf{F}eedback-\textbf{A}ware \textbf{C}redit \textbf{A}ssignment (\textsc{FACA}), which aligns each reaction with that segment, derives a locally normalized reaction advantage, and adds it to verified terminal outcome advantage without an extra critic or rollout. Against an outcome-only Interactive GRPO control matched in simulator, visible dialogue, initialization, rollout, and optimization, \textsc{FACA} improves the nine-domain $τ$-family average across three independently trained runs by 5.91 and 10.22 percentage points at 8B and 14B, respectively. Gains concentrate in Telecom; at 8B, randomizing reaction polarity removes the Telecom gain. The same ordering holds zero-shot on Pare-Bench and Co-Gym. These results demonstrate that next-turn user reactions provide actionable local credit for improving multi-turn user-interacting agents.
Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approaches either rely on process evaluators, which incur annotation and inference costs, or derive step-level credit from successful trajectories. However, successful trajectories are extremely scarce during early-stage reinforcement learning, substantially weakening anchor-based methods. We propose Transition-wise Rubric Credit Assignment (TRCA), which derives step-level supervision directly from action-induced transitions without learned evaluators or successful anchors. TRCA evaluates each transition using Evidence, Execution, and Invalidity rubrics to capture task-relevant information acquisition, valid task execution, and invalid or regressive behavior. From these judgments, Foundational Rubric Reward measures local transition quality, while Breakthrough Rubric Reward tracks newly covered Evidence and Execution conditions to reward incremental task progress. Combined with terminal outcomes, these signals produce fine-grained step-level advantages for policy optimization. Experiments on ALFWorld, WebShop, and seven search-augmented question-answering benchmarks show consistent improvements over the evaluated baselines. With Qwen2.5-7B-Instruct, TRCA improves the WebShop score by 6.0%-12.6%; with Qwen2.5-3B-Instruct, it improves the average SearchQA score by 1.9%-18.3%. These results demonstrate the effectiveness of transition-wise rubric credit assignment for long-horizon tasks with sparse successful anchors.
Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its trajectory-level credit assignment conflates heterogeneous per-turn outcomes into a single reward signal. On-policy distillation provides dense per-token supervision but is either teacher-bounded or prone to gradient concentration collapse. We introduce $\textbf{CrEST}$, a hierarchical credit assignment framework that retains RL's verifier-bounded ceiling while incorporating dense token-level signals from a privileged self-teacher. $\textbf{CrEST}$ resolves credit at two levels: turn-segmented verified advantages address inter-turn dilution, while entropy-gated self-teacher modulation refines intra-turn token contributions. Experiments on BFCL V3 and WildToolBench show that $\textbf{CrEST}$ consistently outperforms both RL and distillation baselines across two model scales, with the largest gains on long-trajectory and strict session-level metrics. Our work demonstrates that the teacher's role in policy optimization can be reduced from determining update directions to modulating update magnitudes, unlocking dense credit assignment without sacrificing the verifier-bounded ceiling.
Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment. On-policy self-distillation (OPSD) addresses this by using the model's own logits as dense token-level teachers, but extending it to search agents introduces a fundamental tension: the teacher, having access to privileged information such as the correct answer, produces a distribution that differs systematically from the student's exploration-based reasoning, and naive distillation causes the student to inherit this information asymmetry rather than learn better search strategies. We resolve this tension through two contributions. First, we construct Evidence Anchors, which are concise, step-level evidence snippets extracted from the web, as privileged information that captures key reasoning steps without revealing the entire answer path. Second, we propose Step-Level Self-Distilled Policy Optimization (SSPO), which converts teacher-student disagreement into step-level advantage weights within GRPO, applied exclusively to incorrect trajectories. This design decouples what to update from how much to update: the outcome reward determines the direction of policy change, while the teacher modulates its magnitude at each step. Correct trajectories are left untouched, preserving their diversity. On Qwen3-8B, SSPO consistently outperforms GRPO across BrowseComp, GAIA, and FRAMES, surpassing or matching GRPO trained with twice as many gradient steps while adding only about 5 percent overhead per step from a single additional forward pass.
Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly rely on coarse prompt-level differentiation without parameter adaptation for diverse subtasks, resulting in insufficient inter-agent heterogeneity and limited specialized capability that bottleneck performance on tasks with complex requirements. To address this, we introduce a Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts (MoRSE) that distinguishes agents with (role, subtask)-conditional specialization at both the task structure and parameter levels. To make agents' responsibility explicit at the task structure level, we formulate a task-oriented multi-agent system that decomposes each task into a dependency-aware Directed Acyclic Graph of subtasks and assigns each agent a specific (role, subtask), introducing task-level specialization across collaborating agents. Additionally, to address the diverse role and subtask parameter adaptation demands, we propose a dynamic Mixture of (role, subtask) LoRA Experts module with a prototype-based semantic router for subtasks, augmenting agents with parameter-level specialization on a shared LLM substrate cost-effectively. Then, to co-optimize experts and router stably under sparse task rewards, we further propose a hierarchical group-relative policy optimization with two-layer credit assignment that isolates expert updates from the cross-route variance introduced by routing decisions, disentangling expert quality from routing quality. Experiments on code-generation benchmarks across three backbones demonstrate the effectiveness of our approach, with improvements in both whole-task and step-wise performance, and the gains from trained specialization generalize across held-out task categories and domains.
Yifu Huo, Shunjie Xing, Chenglong Wang +8cs.LG cs.CL
Agentic reinforcement learning (RL) often suffers from delayed and sparse rewards in real-world environments. A promising solution to this challenge is credit assignment, which aims to decompose trajectory-level rewards and provide more fine-grained supervision for intermediate decisions. However, existing credit assignment approaches ignore the rich process information naturally generated during environment interaction, e.g., interaction history. We argue that such information provides valuable supervision for identifying the contribution of individual actions. To this end, we propose Environmental Feedback-based Credit Assignment (EFCA), a multi-timescale credit assignment approach for long-horizon agentic RL. EFCA complements the long-term outcome signal with two environment-grounded process signals: a short-term feedback signal that captures the immediate effect of the current action and a medium-term state-history signal that identifies ineffective patterns from recent interactions. Both signals are directly extracted from environment feedback and integrated through a return reweighting mechanism. Experiments on ALFWorld and WebShop demonstrate that EFCA consistently improves both task success and task quality over strong baselines, highlighting the effectiveness of environment-grounded multi-timescale credit assignment for long-horizon agentic RL.
Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for training these agents typically treat all steps within a trajectory uniformly during both supervised fine-tuning (SFT) and reinforcement learning (RL), failing to distinguish useful actions from erroneous or redundant ones. In this paper, we propose Answer-Backtracked Credit Assignment (ABC), a fine-grained credit assignment framework for training long-horizon search agents by converting sparse trajectory-level outcomes into dense step-level supervision that rewards useful actions (even in failed trajectories) while suppressing erroneous or redundant actions. Specifically, given a potentially obscure query and its corresponding ground-truth answer, ABC first performs Answer-Backtracked Clue Recovery, which traces back from the answer to recover intermediate clues required to solve the question. It then applies Clue-Anchored Step Scoring to evaluate each search step against these clues, converting sparse binary outcome supervision into dense step-level rewards. Based on these rewards, we develop ABC-SFT, which reweights the loss of each turn, and ABC-GRPO, which uses the step-level scores as rewards in GRPO. Building on this framework, we train ABSeeker based on Qwen3.5-4B with only 8.5k examples. ABSeeker achieves 37.3% on BrowseComp and 39.1% on BrowseComp-ZH. With context management, the scores further improve to 55.3% and 52.9%, respectively, significantly outperforming same-scale (4B) agents and even matching the performance of larger ones (approximately 30B). These results demonstrate the effectiveness of answer-backtracked step-level credit assignment for training long-horizon search agents.
Agent skills are increasingly optimized by automated feedback loops, producing long structured artifacts whose internal value remains unclear. We study skill valuation: assigning credit to the internal units of a fixed skill, such as rules, examples, scripts, and heuristics, under a fixed agent and held-out task distribution. Skill valuation differs from data or prompt-span valuation because skill units are structured: they may depend on other units, belong to a document hierarchy, trigger agent behavior, and consume limited prompt context. We introduce SkillSV, a structure-aware Shapley-style framework for skill valuation. SkillSV compiles a skill into units, dependencies, and hierarchy, so that only valid counterfactual skills are evaluated. It uses paired deletion and length-neutral padding to separate content value from context cost, and estimates the resulting values with a rollout-budgeted estimator for noisy agent evaluations. On four agentic benchmarks, we assess the faithfulness, actionability, and explanation of SkillSV: it recovers unit interactions, preserves aggregate skill lift, and guides safe pruning and compression.
Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning methods often rely on trajectory-level supervision, limiting fine-grained credit assignment in long-horizon TIR scenarios. On-policy self-distillation offers denser signals through teacher branches with privileged context, but existing approaches typically derive such context from ground-truth answers or retrieved skills, which may not reflect the states actually visited by the agent. Moreover, token-level supervision fails to capture the turn-level structure of tool interactions. To address this, we propose TurnSight, a turn-level hindsight self-distillation framework that derives supervision directly from execution-conditioned hindsight. It then constructs multiple hindsight views with different lookahead horizons and selects reliable supervision through cross-horizon directional agreement. Finally, the selected hindsight signal is normalized across sibling rollouts and used to adaptively modulate RL advantages while preserving their original optimization direction. Extensive experiments on three benchmarks demonstrate the effectiveness of TurnSight. Our codes are available at https://github.com/quchangle1/TurnSight.
Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood. We study this on fully-observable two-player zero-sum games, which provide ground-truth evaluation: outcomes are determined by the rules, and optimality of individual moves can be computed or approximated, without relying on a judge model. Across model tiers, LLMs play suboptimally in simple games such as tic-tac-toe or Connect Four, and lose to MCTS opponents. Obfuscations that preserve the game tree but rewrite its surface form leave performance largely unchanged, indicating the gap is not fully explained by recall of memorized strategies. Motivated by this performance gap, we introduce an agentic framework enhanced with an experience memory designed for the sequential setting and addressing common challenges of sequential decision-making such as credit assignment. We show that post-game reflection and rule extraction yield measurable improvements on tic-tac-toe without modifying the model weights.
Multi-agent reasoning (MAR) improves reasoning reliability through iterative solution exchange and refinement. Existing adaptive MAR methods typically learn routing decisions from query-level labels or trajectory-level returns, but such coarse supervision cannot accurately estimate the state-conditioned utility of individual operators in multi-step collaboration. We propose TreeCredit, a shared-prefix credit assignment framework for efficient adaptive MAR. Its core insight is to estimate operator utility through state-matched downstream comparisons, rather than directly attributing trajectory-level outcomes to preceding decisions. TreeCredit constructs shared-prefix collaboration trees by expanding candidate operators from the same intermediate state and assigns each state--operator pair a correctness-prioritized suffix credit based on the terminal correctness and cumulative additional cost of its complete continuation. These structured credits are converted into state-local operator preferences to train a lightweight pairwise state router, which dynamically selects the next admissible operator during inference. Experiments on six reasoning benchmarks show that TreeCredit modestly improves accuracy while substantially reducing inference cost, achieving a better accuracy--cost trade-off than representative MAR methods.
Long-horizon video editing agents receive final-product feedback only after many interdependent decisions. Yet editing quality is subjective, admits multiple valid solutions, and is not meaningfully calibrated across heterogeneous requests, making a global scalar objective both ambiguous and temporally uninformative. Our key observation is that fixing the request, materials, and production constraints converts this subjective objective into an ordinal comparison among directly comparable alternatives. We introduce Group-Relative Preference Backpropagation (GRPB), which transforms same-task rankings into zero-sum advantages and redistributes them as bounded credit over semantic editing segments. A lagged allocator and guarded transmission prevent current judgments or unreliable estimates from directly shaping the same rollout group. We manually construct a project-disjoint, horizon-stratified suite of realistic editing tasks for training and controlled evaluation. Across matched baselines, credit interventions, external benchmarking, and blinded human evaluation, GRPB improves both editing behavior and rendered products. The resulting 9B Crayotter model surpasses several proprietary systems on AgenticVBench, supporting task-local preference reduction as a practical approach to learning from subjective, delayed outcomes. Code and all supporting materials are publicly available at https://github.com/idwts/Crayotter.
Multi-step search is a fundamental capability for search agents, enabling them to iteratively acquire, refine, and integrate external evidence for complex reasoning QA. However, vanilla GRPO allocates rewards exclusively based on the model's final outputs, yielding outcome-only supervision with no supervisory signals for intermediate reasoning steps. Such sparse supervision easily causes training instability and redundant search behaviors on multi-step search tasks. To mitigate this limitation, we adopt process reward to deliver stepwise supervision signals. For this process reward, we propose two complementary criteria to judge each search step: whether the step yields new evidence to facilitate problem solving, and whether it forms an efficient, pivotal intermediate decision within the overall reasoning trajectory. Building on this insight, we propose BiCAA: a bidirectional credit assignment framework that delivers dense, distinguishing process rewards for search-augmented agents. BiCAA builds bidirectional process rewards by fusing two complementary signals: forward solvability gain and hindsight success criticality. The former quantifies step-wise improvements in answer plausibility, while the latter evaluates each step's necessity for final success via hindsight outcome-based criticality scoring. We modulate and aggregate the two signals and then fuse them with the outcome reward. Experiments on search-augmented QA benchmarks show that BiCAA stabilizes policy optimization, reduces redundant search behavior, and achieves competitive performance.
The rapid development of Large Language Models (LLMs) has opened new avenues for Automated Heuristic Design (AHD) for solving NP-hard combinatorial optimization problems (COPs). However, existing LLM-driven AHD methods are largely confined to rigid solver templates, relegating the search process to isolated module tuning. Transitioning to fully autonomous, system-level algorithm design is essential but fraught with low reliability of generated operators, extremely large search spaces, and ineffective credit assignment. To overcome these drawbacks, this paper proposes a Directed Graph-Guided Automated Algorithm Design framework, termed DGA$_2$D. It structures the open-ended program space as a directed graph, where each node represents a functional operator that can be instantiated using one of multiple candidate code implementations, while directed walks constitute complete algorithmic pipelines. A first-order path-dependent credit assignment mechanism is introduced to evaluate code variations strictly based on their topological context. Extensive experiments across 12 distinct COPs, ranging from complex scheduling to routing, demonstrate the consistent empirical advantages of DGA$_2$D. It reduces the average normalized gap by up to 10.96 percentage points compared to state-of-the-art LLM baselines.
Zhiyuan Yao, Yuxin Chen, Zhengxi Lu +13cs.LG cs.AI
Large language model agents often encounter related yet distinct tasks that share reusable solution patterns. Yet standard agentic reinforcement learning treats tasks as independent episodes, while existing approaches to skill learning either focus on repeated attempts of one task or use pipelines with multiple stages that entangle extraction, retrieval, and execution. We introduce SkillRise, a unified reinforcement learning framework for learning skills across tasks. SkillRise organizes related instances into progressively challenging sequences and uses a single policy to alternate between task solving and curating an evolving skill document passed directly to the next task. Decoupled credit assignment across tasks supervises solving with the current task outcome and curation with discounted downstream outcomes. Experiments on ALFWorld, WebShop, and ScienceWorld show that SkillRise achieves the strongest Pass@1 performance among the compared methods, with gains over the strongest baseline ranging from 2.3 to 8.5 percentage points. Although trained across distinct tasks, its learned curation policy remains effective for repeated attempts on the same task. Further analysis reveals scaling at test time across tasks: performance improves with longer sequences of related tasks even when each task is attempted only once. This trend suggests that SkillRise reuses transferable skills across tasks rather than benefiting from repeated sampling of the same task. SkillRise further retains strong performance while substantially reducing the runtime overhead of skill learning pipelines with multiple stages. Together, these results provide a simple and efficient training paradigm for LLM agents to extract, refine, and reuse transferable skills across tasks.