Chenyu Zhou, Qiliang Jiang, Shuning Wu +1cs.LG cs.AI
Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize credit onto the turns that mattered. We identify the structural quantity that predicts when this is the right move, the verifier information density V_d = k/C (the fraction of an agent's C-step causal chain whose per-turn correctness the verifier exposes), and show that terminal-state verifiers sit deep in a low-V_d regime where targeting is the wrong axis. In controlled shared-rollout comparisons on tau^2-bench that separate reward density from credit geometry, a continuous dense reward spread uniformly beats the sparse binary outcome reward (net-harmful on 4/5 seeds), while concentrating the same advantage on progress turns or on random turns is equally harmful: targeting is second-order. The mechanism is coverage: terminal-state verification collapses the observable signal to a single final-write turn (k=1 in 98% of rollouts) while success requires a 5-8 step chain of prerequisite tool calls. A synthetic phase boundary places the crossover at V_d* ~ 0.8, whereas measured V_d is ~0.15 on tau^2-bench and ~0.4 on BFCL V3; uniform also wins on BFCL, where a matched-concentration shuffled control is negative on 8/8 seeds. The effect reproduces across model families on ToolACE-2-8B (Delta = -0.048 over 32 pre-registered seeds; an independent 20-seed replication is itself significant), and a pre-registered matched-budget breadth sweep traces a monotone dose-response whose deficit vanishes only at full chain coverage, with a reward-to-go arm reaching full-coverage parity. Uniform redistribution is the zero-information coverage default that per-turn schemes must beat; we contribute the matched-concentration shuffled control that any targeting claim should clear.
Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costly for long and variable tool-use trajectories. Single-stream Policy Optimization (SPO) removes this dependency with a persistent prompt-level value estimate, but its recipe whitens one advantage per trajectory before optimizing a token-mean actor loss. We show that trajectory centering generally does not center the token-weighted quantity consumed by the actor, and fix the mismatch by standardizing terminal-outcome advantages under the action-token measure. We additionally organize prompt evidence by the policy event that generated it rather than learner receipt order. Across matched runs on ALFWorld at two model scales and on Math-TIR, SPO++ improves online learning efficiency over SPO. A paired ablation identifies action-token-measure normalization as the strongest tested component.
Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantages from multiple rollouts, avoiding the substantial memory overhead of conventional proximal policy optimization (PPO) and achieving strong performance on long-horizon interactive tasks. Despite their success, recent studies revealed three limitations: (1) Lack explicit value generalization and effective temporal credit assignment; (2) Suffer from potential advantage collapse in long-horizon complex tasks; (3) Require a costly trade-off between sampling budget and policy performance. In this work, we propose Single-rollout Autoregressive Policy Optimization (SAPO), a low-memory and compute-efficient framework in which the policy and value functions share a single autoregressive backbone. SAPO exploits the autoregressive structure of LLMs to produce policy and value predictions at distinct causal boundaries with shared parameters, while independently optimizing the PPO objectives and auxiliary on-policy SARSA objectives. To robustly estimate the contribution of each turn, we further introduce a trajectory-level generalized advantage estimator that combines lambda-returns with batch normalization. Experiments across ALFWorld and WebShop with Qwen2.5-1.5B/7B show that SAPO trains stably and outperforms PPO and GRPO by mean +15.1 and +12.1 percentage points, respectively, while eliminating the memory cost of a separate critic model and reducing per-iteration runtime by 33.2% over PPO.
Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards. However, a completed rollout can yield many such signals, leaving their appropriate allocation across turns unclear. We introduce TRIAL, a trajectory-relative hindsight distillation framework with a unified turn-aligned scoring protocol. For each decision turn, TRIAL extracts an outcome view of that decision's realized consequence and evaluates the same response under ordinary and hindsight-conditioned contexts. The signed log-probability gap determines the direction and local strength of token-level supervision, while turn-level magnitudes are normalized jointly over the realized trajectory. The resulting allocation multipliers have an eligible-token-weighted mean of one, redistributing dense supervision across turns while fixing its average multiplier. Experiments on WebShop and ALFWorld with different backbones show that TRIAL outperforms GRPO across all eight combinations of backbone, environment, and evaluation metric, while achieving the best or tied-best performance among six methods on six of them. On WebShop with Qwen3-1.7B, TRIAL improves the success rate from 56.4% to 75.2% and the task score from 78.7% to 85.7%. Controlled ablations further show that trajectory-relative turn allocation provides substantial gains beyond those of dense hindsight distillation alone.
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao +10cs.AI cs.LG
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes in long-horizon, multi-turn agentic tasks. Recent work introduces privileged self-distillation for credit assignment, providing denser supervision, but it remains unclear how such local signals should represent sequential credit. We propose AgentOPSD, a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning. AgentOPSD aggregates token-level teacher-student log-probability gaps into turn-level evidence and recursively updates a Bayesian belief state in log-odds space. This yields a principled reweighting scheme that converts sparse outcome supervision into turn-level credit signals and identifies pivotal turns through the marginal belief revision between consecutive states. The method is fully compatible with standard policy optimization and requires neither an additional critic nor extra rollouts. We evaluate AgentOPSD on ALFWorld, WebShop, and Search-QA using Qwen2.5 models at two scales (3B and 7B). AgentOPSD outperforms GRPO and strong self-distillation baselines, achieving 89.1% success on ALFWorld with Qwen2.5-7B. Ablation studies attribute the gains to turn-level aggregation and history-dependent recursive belief updates.
Muon is competitive with AdamW in large-scale pre-training, but its operating regime in reinforcement-learning post-training remains unclear. We map this regime on ALFWorld, a sparse-reward agentic benchmark, using three group-based objectives and Qwen2.5 models from 0.5B to 3B. Under a shared KL and clipping recipe, matched optimizer comparisons and AdamW rate controls trace the usable step-size range. AdamW responds non-monotonically to rate, whereas fan-in Muon remains stable at a more aggressive effective step: at $3 \times 10^{-5}$ it improves late success over an AdamW $10^{-6}$ baseline after correction across rate-metric tests. Its normalized-AUC effect is directionally positive but less uniform; the heuristic-matched lower-rate effect is less consistent, and tuned AdamW nearly matches high-rate Muon at 3B GraphGPO. High-rate Muon applies $3.53 \times$ AdamW's hidden-matrix update RMS; a full-budget RMS-matched control removes the late-success gain. Together, these results identify a recipe-level operating regime in which fan-in Muon supports a more aggressive stable effective step under shared KL and clipping: the margin is largest when optimization headroom remains and contracts near saturation, after AdamW tuning, or under magnitude matching. The scale-matched control ties this spectral effect to Muon's scale convention rather than establishing a universal optimizer ranking. Code is available at https://github.com/x66ccff/verl-muon.
Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training. Outcome rewards provide reliable supervision for short-horizon reasoning, but become sparse and high-variance as trajectories grow to tens or hundreds of tool calls. They can also be misleading: a failed rollout may contain many useful actions that move the agent closer to the goal, yet outcome-only training assigns them the same negative advantage as the eventual mistake. We propose TRACE (Turn-level Reward Assignment via Credit Estimation), a dense credit-assignment method for agentic reinforcement learning. TRACE represents rollouts as state transitions at tool-call boundaries, obtains gold-answer log-probabilities from a frozen reference model, transforms them into log-ratio state values, and derives per-action rewards as Temporal-Difference changes in those values. This requires no additional critic or process-label training, and its one-step log-ratio TD component telescopes across redundant tool calls. On long-horizon complex search, TRACE substantially improves base-model tool-use ability using pure RL, without a cold-start supervised fine-tuning stage, an agentic mid-training stage, or training on live-web data. On the closed-web BrowseComp-Plus benchmark, it raises Qwen3-4B from $7.2$ to $35.6$ and Qwen3-30B-A3B from $8.4$ to $42.6$. The learned search behavior also transfers to open-web benchmarks, and the learning curves show earlier improvement and faster convergence during RL training.
Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agents on long-horizon interactive tasks. To obtain finer-grained policy updates than trajectory-level optimization, recent work has moved toward step-level group-based RL, where intermediate steps are grouped and compared within a rollout batch. However, step-level advantage estimation is sensitive to how groups are formed: grouping by broad state keys improves coverage but may compare actions taken under different histories, while enforcing historical consistency yields fairer comparisons at the cost of fragmented groups and missing peer-comparison signal. In this paper, we propose ProGPO (Progress- and Reliability-Oriented Group Policy Optimization), a learned-critic-free method for context-consistent step-level learning. ProGPO keeps exact-prefix action comparison, and complements sparse peer comparisons with transition credit derived from rollout-based state potentials. To estimate these potentials reliably, ProGPO combines semantic expansion with inverse-variance fusion across history depths. We evaluate ProGPO on two challenging agentic tasks, ALFWorld and WebShop, with Qwen2.5-1.5B-Instruct. Results show that ProGPO improves over matched agentic RL baselines under comparable computational overhead, and additional Qwen2.5-3B-Instruct experiments further test the scalability of the proposed method.
Yuanda Xu, Zhengze Zhou, Hejian Sang +5cs.LG cs.AI
Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uniform advantage over all action tokens. This outcome signal is useful but structurally incomplete: it punishes useful exploration in failed rollouts and reinforces redundant or regressive actions in successful rollouts. We propose TRIAGE, a role-typed credit assignment framework that adds a semantic role axis to outcome credit. A structured judge classifies each segment as decisive progress, useful exploration, no-progress infrastructure, or regression, and a fixed role-conditioned rule maps these labels to bounded segment-level process rewards. This keeps verifier outcomes as the source of optimization direction while correcting the two main blind spots of outcome-only credit. We further show that role-conditioned credit is the optimal segment-level correction expressible from role labels alone -- a projection of the per-segment advantage residual onto the role variable -- so that the fixed role constants reduce advantage estimation error whenever the judge is reliable, and we connect this to lower-variance policy gradients. Across ALFWorld, Search-QA, and WebShop, TRIAGE improves success rates over GRPO for two policy models and outperforms both a scalar judge-derived process reward and an outcome-supervised shared-backbone value baseline. Ablations show that the gain comes from role typing rather than merely adding dense rewards: reliable detection of regression inside successful trajectories is the dominant contributor, while exploration credit provides a consistent secondary gain; on completed ALFWorld and WebShop rollouts, TRIAGE also reduces environment-facing turns by an additional $10.4\%$ and $14.8\%$ relative to GRPO.
Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context. The prevailing recipe gates this loss by a single scalar, the teacher-student log-probability gap. This signal is doubly limited: it is retrospective, scoring only the realised rollout and never the counterfactual ones, and it is sign-blind, never signalling when a teacher-preferred action would have harmed the trajectory. We introduce CRAFT, a three-pillar credit-assignment scheme that addresses both limitations. Pillar 1, Counterfactual Token Importance, reuses the G-1 sibling rollouts that GRPO already samples and importance-weights them by the log-probability gap to form a self-normalised estimate of the group-level counterfactual change in advantage from up-weighting teacher-preferred actions at each step; this yields a signed per-token credit at near-zero extra compute. Pillar 2 is an asymmetric controller that raises the distillation weight as it lowers the reference-KL weight along an exponential moving average of gate activity, and conversely. Pillar 3 polarises the KL penalty token by token, switching between a mode-seeking and a mode-covering update according to the sign of the credit. Each pillar has an independent switch that, when disabled, renders the loss and gradient byte-identical to the baseline in IEEE-754 arithmetic, so any measured gain is attributable to algorithmic change rather than implementation drift. We prove the estimator's consistency and a variance bound, give structural and bit-exact reproducibility guarantees, and evaluate CRAFT across three agentic environments, four model scales, and five end-to-end methods, plus two tabulated prior-work baselines. Among these is Adaptive-CRINGE, a comparator sharing Pillar 2 with CRAFT, isolating the counterfactual contribution.
Yunan Wang, Minghui Song, Zihan Zhang +6cs.LG cs.AI cs.CL
Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, recent agentic RL frameworks have shifted from trajectory-level to step-level training. However, long-horizon agentic RL suffers from severe reward sparsity and delay, as feedback is often deferred for dozens of interaction steps. While existing step-level frameworks refine training granularity, their credit assignment remains coarse-grained and still treats agent exploration as isolated, linear trajectories. This oversimplified perspective ignores the inherent graph structure of state transitions, leading to high-variance state-value estimation and myopic, localized credit assignment. To overcome these critical bottlenecks, we propose Group-Graph Policy Optimization (G2PO), a novel group-based RL algorithm tailored for multi-turn agentic tasks. G2PO explicitly transforms linear interaction trajectories into a global state-transition graph. By aggregating identical observations across different trajectories, we introduce group-aggregation state-value estimation that reduces sampling variance and trajectory-dependent bias. Furthermore, we redefine agent actions as transitions between state nodes and propose an edge-centric advantage estimation strategy. By globally standardizing Temporal Difference (TD) errors across the entire graph, G2PO explicitly identifies and prioritizes critical transitions that drive absolute task progress. Extensive experiments on representative long-horizon benchmarks-WebShop, ALFWorld, and AppWorld-demonstrate that G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.
Reinforcement learning (RL) has emerged as a powerful paradigm for training Large Language Models (LLMs) as agents. However, conventional RL methods for long-horizon agentic tasks often struggle with sparse outcome rewards. Intuitively, this overlooks the rich environment dynamics information contained in rollout interaction trajectories. We argue that the interaction experience inherently serves as an implicit supervision signal, reveals the underlying transition mechanisms of the environment, and enables the agent to construct a more accurate internal model of the environment.. Therefore, in this work, we investigate how to leverage this additional signal to improve policy learning. Specifically, we propose EnvRL, a framework that incorporates environment dynamics learning into agentic RL via two auxiliary objectives: state prediction and inverse dynamics. By jointly optimizing with the primary RL objective, we encourage the agent to internalize environment dynamics from its own interaction experience. Extensive experiments on two long-horizon agentic benchmarks demonstrate that EnvRL achieves significant improvements on success-rates over RL-only baselines, e.g., when trained with GRPO, lifting Qwen-2.5-1.5B-Instruct from 72.8% to 77.4% on ALFWorld, and from 56.8% to 67.0% on WebShop.
LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and tool outputs. A well-functioning agent should be able to leverage this feedback to accurately assess its own performance. Yet we find a persistent reflection gap: LLM agents tend to mis-assess their own outputs after observing concrete environment feedback -- even for questions they correctly answered -- and standard RL barely helps due to a credit-assignment mismatch. To close this gap, we propose RefGRPO, a simple yet effective fix that augments standard RL algorithms with two key ingredients: a free calibration bonus computed by contrasting the agent's own reflection with the actual outcome (requiring no additional reward model, LLM judge, or external annotation), and a dynamic schedule on its coefficient. Compared to standard RL baselines, our method simultaneously improves reflection calibration (e.g., reduces underconfidence rate $44.4\% \to 7.7\%$) and task accuracy (e.g., $75.1\% \to 76.5\%$) on text-to-SQL across five benchmarks. The resulting calibrated reflection turns the agent into its own verifier grounded in environment feedback, which further enables (i) better self-improvement that uses reflections as pseudo-rewards without outcome supervision, and (ii) more effective test-time selective prediction by committing only to rollouts flagged as correct.
Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing methods assign credit over coarse heuristic units, such as tool-call boundaries or fixed workflows, making it difficult to identify which intermediate decisions influence downstream outcomes. In this work, we study agentic RL from two perspectives: \textit{where to branch and how to assign credit after branching}. Our pilot analysis shows that influential decision points are broadly distributed throughout the generated sequence rather than concentrated at tool calls, while token entropy alone does not reliably reflect their impact on final outcomes. Motivated by these observations, we propose \textbf{Agentic Procedural Policy Optimization (APPO)}, which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequence. APPO selects branching locations using a Branching Score that combines token uncertainty with policy-induced likelihood gains of subsequent continuations, enabling more targeted exploration while filtering out spurious high-entropy positions. It further introduces procedure-level advantage scaling to better distribute credit across branched rollouts. Experiments on 13 benchmarks show that APPO consistently improves strong agentic RL baselines by nearly 4 points, while keeping efficient tool-calls and maintaining behavior interpretability.
Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.
SWE-bench-style agentic reinforcement learning relies on expensive stateful trajectories, yet substantial compute is wasted on sampled rollout groups with skewed pass rates, where binary rewards provide a weak contrastive signal. We frame this inefficiency as a pass-rate control problem and show that a 50% pass rate is the most informative operating point: it maximizes reward entropy, the probability of surviving group filtering, RLOO advantage energy under GRPO, and success--failure contrastive structure. Guided by this principle, we propose Prefix Sampling (PS), which replays trajectory prefixes to steer skewed groups toward this regime: successful prefixes serve as head starts for mostly failing groups, while failing prefixes serve as handicaps for mostly passing groups. In stateful agent environments, prefix states are reconstructed through replay while replayed tokens are excluded from the loss, restricting optimization to continuations generated by the current policy. On SWE-bench-style agentic RL, PS delivers end-to-end wall-clock speedups of 2.01x on Qwen3-14B and 1.55x on Qwen3-32B while preserving or improving final verified performance. For 14B, the SWE-bench Verified peak rises from the baseline peak of 0.273 to 0.295 under PS. Additional mathematical reasoning experiments on AIME 2025 show the same pass-rate control pattern and decompose the gains into replay, bidirectional coverage, and adaptive control.