Credit Assignment in RL

Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision. While finer-grained credit assignment is promising for effective policy updates, obtaining reliable local credit and assigning it to the right parts of the long-horizon trajectory remains an open challenge. In this paper, we propose Granularity-adaptivE Advantage Reweighting (GEAR), an adaptive-granularity credit assignment framework that reshapes the trajectory-level GRPO advantage using token- and segment-level signals derived from self-distillation. GEAR compares an on-policy student with a ground-truth-conditioned teacher to obtain a reference-guided divergence signal for identifying adaptive segment boundaries and modulating local advantage weights. This divergence often spikes at the onset of a semantic deviation, while later tokens in the same autoregressive continuation may return to low divergence. GEAR therefore treats such spikes as anchors for adaptive credit regions: where the student remains aligned with the teacher, token-level resolution is preserved; where it departs, GEAR groups the corresponding continuation into an adaptive segment and uses the divergence at the departure point to modulate the segment' s advantage. Experiments across eight mathematical reasoning and agentic tool-use benchmarks with Qwen3 4B and 8B models show that GEAR consistently outperforms standard GRPO, self-distillation-only baselines, and token- or turn-level credit-assignment methods. The gains are especially strong on benchmarks with lower GRPO baseline accuracy, reaching up to around 20% over GRPO, suggesting that the proposed adaptive reweighting scheme is especially useful in more challenging long-horizon settings.

Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet existing approaches predominantly rely on sparse outcome-level feedback, posing a substantial credit-assignment challenge in long-horizon agentic tasks. In this work, we study structured agentic reasoning problems that admit symbolic or algorithmic task-solving oracles. We propose Verifiable Process Rewards (VPR), a training framework that repurposes such task oracles as action-level process verifiers, providing dense rewards for intermediate actions and enabling fine-grained credit assignment. We instantiate VPR in three distinct settings: a search-based oracle for Sokoban, a constraint-based oracle for Sudoku, and a posterior-based oracle for Minesweeper. To optimize policies with these rewards, we introduce oracle-guided state-group rollout and locally normalized optimization. Empirically, VPR-trained Qwen3-4B outperforms outcome-reward GRPO and VinePPO across all three training environments. When jointly trained on math data and all three game environments, VPR achieves the highest average general-reasoning performance and strongest agentic results among the compared training configurations. To further assess its applicability to more general agentic tool-use settings, we apply VPR-style action-level supervision to $τ^2$-bench using an expert LLM as a reference policy and observe improved performance over outcome-reward GRPO on held-out tasks. Together, these results position VPR as a promising approach for leveraging reliable task oracles to improve agentic reasoning, while highlighting its dependence on the availability and reliability of task oracles and the challenge of extending intermediate verification to less structured, open-ended environments.

Large Language Model (LLM)-based search agents trained with reinforcement learning (RL) have significantly improved the performance of knowledge-intensive tasks. However, existing methods encounter critical challenges in long-horizon credit assignment: (i) Reward Sparsity, where models receive only outcome feedback without step-level guidance to differentiate action quality; (ii) Isolated Credit, where credit is assigned to steps independently, failing to capture sequential dependencies; and (iii) Distributional Shift, where rewards are estimated on templates that deviate from the model's natural generative distribution. To address these issues, we propose Pivot-Based Credit Assignment (PiCA), a novel step reward mechanism that reformulates the search trajectory as a sequential process of cumulative search progress. Unlike prior isolated step rewards, PiCA defines process rewards as success probabilities dependent on the historical context based on Potential-Based Reward Shaping (PBRS). This approach identifies pivot steps, which comprise target golden sub-queries and sub-answers derived from historical trajectories, as information peaks that significantly boost the likelihood of a correct final answer. By anchoring these step rewards to the final task objective, PiCA provides dense, pivot-aware and trajectory-dependent guidance while maintaining distributional consistency. Extensive experiments show that PiCA outperforms existing strong baselines across seven knowledge-intensive QA benchmarks, achieving 15.2% and 4.4% improvements for 3B and 7B models. The consistent performance gains across various models show PiCA's robust generalization. The code is available at https://github.com/novdream/PiCA.

Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We present BoostAPR, a three-stage framework addressing these challenges: (1) supervised fine-tuning on execution-verified demonstrations with reasoning traces, (2) training dual reward models--a sequence-level assessor and a line-level credit allocator--from execution outcomes, and (3) PPO optimization where the line-level model redistributes rewards to critical edit regions. This line-level credit assignment operates at an intermediate granularity naturally suited to code changes. Trained on SWE-Gym and evaluated on four benchmarks, BoostAPR achieves 40.7% on SWE-bench Verified (+22.9pp over base model), 24.8% on Defects4J (Python-to-Java transfer), 84.5% on HumanEval-Java, and 95.0% on QuixBugs, achieving competitive results among open-source models with strong cross-language generalization.

Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns. Recent training-based multi-turn jailbreak methods learn long-horizon attack strategies from interaction feedback, but often rely on coarse trajectory-level outcome signals that broadcast uniformly to every turn. However, we find that turn-level contributions in multi-turn jailbreaking are non-uniform, phase-dependent, and target-specific. Such coarse outcome supervision induces a credit assignment problem, leading to over-rewarding redundant turns in successful trajectories and under-crediting useful intermediate turns in failed ones. To address this, we propose TRACE, a turn-aware credit assignment framework for reinforcement learning (RL)-based multi-turn jailbreaking. For successful trajectories, TRACE estimates turn-level contributions via leave-one-turn-out semantic masking; for failed ones, TRACE assigns penalties based on prompt harmfulness and semantic relevance, with an additional local refusal-aware penalty. Furthermore, we reuse the attack-side credit signal for multi-turn defense alignment. Extensive experiments on open-source and closed-source targets show that TRACE achieves strong overall performance in effectiveness, transferability, and efficiency, yielding about a 25% relative improvement in attack success rate over the strongest RL baseline while also improving the safety-utility balance when reused for defense alignment.

Command line interface (CLI) agents are emerging as a practical paradigm for agent-computer interaction over evolving filesystems, executable command line programs, and online execution feedback. Recent work has used reinforcement learning (RL) to learn these interaction abilities from verifiable task feedback, yet few methods exploit the native structured attributes of CLI actions as learning signals. Beyond this underused action structure, CLI learning also couples two bottlenecks for coding agents. First, the agent must identify task-relevant evidence in a large codebase from partial observations. Second, sparse terminal rewards must be assigned to the actions that shape a long multi-turn trajectory. We study these bottlenecks through shell-driven information extraction and file editing tasks. For selective observation, we introduce $σ$-Reveal, an inference-time mechanism that selects token-budgeted context for the same CLI. For credit assignment, we propose Action Advantage Assignment ($\mathrm{A}^3$), a native agentic RL method that preserves the algorithmic complexity of standard agentic RL. $\mathrm{A}^3$ constructs turn-level advantages from episode-level relative feedback, abstract syntax tree (AST) based action sub-chain residuals, and tree-level trajectory margins. To further evaluate this problem setting, we construct ShellOps, a verifiable dataset suite covering CLI tasks in repository environments.

Communication is fundamental to sustaining reciprocity and cooperation in strategic interactions. We identify and formulate the influence attribution problem as the central optimization difficulty inherent in such dynamics for a learning agent: any action or signal the agent emits reshapes the reputations of many third parties along combinatorially branching paths before feeding back into its own future rewards, forcing the agent to account for all of these indirect channels at once when choosing every action. To address this, we introduce the reciprocity gradient, which explicitly backpropagates reward gradients through private estimators of opponents' policies trained from public observations. The gradient flows through the reputation chain itself analytically, rather than being estimated from sampled returns. It jointly optimizes actions and evaluative signals without intrinsic rewards or reward shaping. Empirically, the method recovers near-optimal context-sensitive policies, while sample-based baselines collapse into constant-output policies.

Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely on biased, high-variance likelihood estimates. We identify two fundamental weaknesses: the absence of temporal credit assignment across the denoising trajectory, and the systematic bias of mean-field likelihood estimates used for policy optimization. To address these, we propose Denoising-Aware Credit Assignment for GRPO (DACA-GRPO), a lightweight, plug-and-play enhancement for any GRPO-style trainer. DACA-GRPO introduces two complementary mechanisms: Denoising Progress Scores, which extract per-token importance weights from intermediate predictions at no additional forward cost, and Stratified Masking Likelihood, which partitions token positions into strata so that each token is predicted with most of the sequence as context, reducing the mean-field bias. Applied on top of three GRPO base methods, DACA-GRPO achieves consistent improvements across seven benchmarks spanning mathematical reasoning, code generation, constraint satisfaction, and constrained generation, with gains of up to 5.6pp on math reasoning, 7.4pp on code generation, 36.3pp on constraint satisfaction, and 5.9pp on JSON schema adherence.

Large language models (LLMs) are increasingly deployed for autonomous financial trading, a domain requiring continuous adaptation to noisy, non-stationary markets. Existing self-improving agents typically address this through unbounded free-form prompt optimization. However, in low signal-to-noise environments with delayed scalar rewards (P&L), this unstructured approach exacerbates the fundamental credit assignment problem: optimizers cannot reliably distinguish systematic logic flaws from stochastic market variance, inevitably leading to policy drift. To overcome this bottleneck, we introduce the Self-Evolving Human-Auditable Rubric Policy (SHARP), a neuro-symbolic framework that replaces unconstrained text mutation with structured, symbolic policy optimization. SHARP confines the agent's reasoning to a bounded, human-readable rubric of explicit condition-action rules. When sub-optimal trades occur, an attribution agent employs cross-sample reasoning across multiple samples to isolate specific rule failures. This enables targeted, atomic policy edits that are subsequently regularized through strict walk-forward validation. Evaluated across three diverse equity sectors and four LLM backbones, SHARP consistently transforms generic initial heuristics into highly robust strategies, lifting the empirical performance of compact models by 10 to 20 percentage points on average (e.g., GPT-4o-mini). Ultimately, SHARP demonstrates that LLMs can achieve dynamic and efficient adaptation while significantly enhancing the structural transparency and auditability demanded by institutional finance.

Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward, making it difficult to evaluate the contribution of individual tool-calls within multi-turn interactions. Existing approaches to such process credit assignment either depend on separate external process reward models that introduce additional consumption, or tree-based structural rollout that merely redistributes the outcome signal while constraining trajectory diversity. A promising alternative leverages the per-turn change in the policy's predicted probability of the ground-truth, termed Information Gain (IG), as an intrinsic process signal without an external evaluator. However, prior work on leveraging IG signals within the RL training loop faces three systematic challenges: normalizing across turns that face heterogeneous positional contexts can distort the relative standing of individual turns, accumulating a variable number of terms causes advantage magnitudes to drift with trajectory depth, and a fixed clipping range governs policy updates identically for turns with vastly different IG signals. In this paper, we propose A$^2$TGPO (Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping), which retains IG as the intrinsic signal but re-designs how it is normalized, accumulated, and consumed: (i) turn-group normalization: normalizes IG within each (prompt, turn-index) group so that each turn is compared only against peers at the same interaction depth; (ii) variance-rescaled discounted accumulation: divides cumulative normalized IG by square root of accumulated terms to keep advantage magnitudes comparable across turn positions; and (iii) adaptive turn-level clipping: modulates each turn's clipping range based on its normalized IG, widening the update region for informative turns and narrowing it for uninformative ones.

While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging. We identify two root causes: credit misattribution, where correct early actions are penalized due to terminal failures, and sample inefficiency, where scarce successful trajectories result in near-total loss of learning signal. We introduce a milestone-guided policy learning framework, BEACON, that leverages the compositional structure of long-horizon tasks to ensure precise credit assignment. BEACON partitions trajectories at milestone boundaries, applies temporal reward shaping within segments to credit partial progress, and estimates advantages at dual scales to prevent distant failures from corrupting the evaluation of local actions. On ALFWorld, WebShop, and ScienceWorld, BEACON consistently outperforms GRPO and GiGPO. Notably, on long-horizon ALFWorld tasks, BEACON achieves 92.9% success rate, nearly doubling GRPO's 53.5%, while improving effective sample utilization from 23.7% to 82.0%. These results establish milestone-anchored credit assignment as an effective paradigm for training long-horizon language agents. Code is available at https://github.com/ZJU-REAL/BEACON.

Reinforcement Learning with Verifiable Rewards (RLVR) has become a key approach for improving the reasoning abilities of large language models. However, widely used critic-free algorithms such as Group Relative Policy Optimization (GRPO) suffer from coarse-grained temporal credit assignment, as they assign the same trajectory-level advantage to all tokens and fail to distinguish the contributions of different reasoning steps. To address this challenge, we propose Selective Successor Eligibility Traces (S-trace), an critic-free eligibility trace method that enables more effective credit assignment. S-trace introduces successor importance reweighting to recover downstream credit signals under PPO-style clipping and propagates them to selected historical tokens through entropy-based token selection. Theoretically, we establish an upper bound on its discrepancy from the raw eligibility traces-based policy gradient estimator, jointly controlled by the KL divergence and the trace decay factor $λ$. Experiments show that S-trace achieves absolute gains in average pass@16 of 1.80% and 6.17% over GRPO, and 2.32% and 0.87% over trace-style GRPO($λ$), on Qwen3-1.7B and Qwen3-4B, respectively, while maintaining robust gains on Qwen3-8B and producing shorter responses.

Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), has advanced LLM reasoning. However, GRPO suffers from three credit assignment failures: uniform token-level granularity that ignores heterogeneous informational value, uniform polarity that penalizes correct steps and rewards incorrect ones, and zero-variance collapse that erases outcome-driven gradients. We systematically quantify these failures, revealing highly non-uniform token informativeness, widespread step-level polarity misalignment, and substantial training waste. To address these limitations, we propose Entropy-Progress Aligned GRPO (EP-GRPO), a framework that mines the model's intrinsic information flow for dense, self-supervised guidance. EP-GRPO integrates entropy-gated modulation to prioritize high entropy decision pivots, implicit process signals from policy divergence anchored to outcome advantages for directional token-level feedback without external reward models, and cumulative entropy mapping that enables progress-aligned advantage normalization, naturally maintaining gradient flow under zero reward variance. Extensive experiments on mathematical reasoning benchmarks demonstrate that EP-GRPO achieves superior accuracy and efficiency compared to GRPO and its variants. The code will be available.

Tool-integrated Text-to-SQL parsing has emerged as a promising paradigm, framing SQL generation as a sequential decision-making process interleaved with tool execution. However, existing reinforcement learning approaches mainly rely on coarse-grained outcome supervision, resulting in a fundamental credit assignment problem: models receive the same reward for any trajectory that yields the correct answer, even when intermediate steps are redundant, inefficient, or erroneous. Consequently, models are encouraged to explore suboptimal reasoning spaces, limiting both efficiency and generalization. To address this problem, we propose FineStep, a novel framework for step-level credit assignment in tool-augmented Text-to-SQL. First, we introduce a reward design with independent process rewards to alleviate the signal sparsity of outcome supervision. Next, we present a step-level credit assignment mechanism to precisely quantify the value of each reasoning step. Finally, we develop a policy optimization method based on step-level advantages for efficient updates. Extensive experiments on BIRD benchmarks show that FineStep achieves state-of-the-art performance and reduces redundant tool interactions, with a 3.25% average EX gain over GRPO at the 4B scale.

Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful to the model that consumes it. This outcome-only signal can reinforce traces that are right for the wrong reasons, overstate reasoning gains by rewarding shortcuts, and propagate flawed intermediate states in multi-step systems. To this end, we propose TraceLift, a planner-executor training framework that treats reasoning as a consumable intermediate artifact. During planner training, the planner emits tagged reasoning. A frozen executor turns this reasoning into the final artifact for verifier feedback, while an executor-grounded reward shapes the intermediate trace. This reward multiplies a rubric-based Reasoning Reward Model (RM) score by measured uplift on the same frozen executor, crediting traces that are both high-quality and useful. To make reasoning quality directly learnable, we introduce TRACELIFT-GROUPS, a rubric-annotated reason-only dataset built from math and code seed problems. Each example is a same-problem group containing a high-quality reference trace and multiple plausible flawed traces with localized perturbations that reduce reasoning quality or solution support while preserving task relevance. Extensive experiments on code and math benchmarks show that this executor-grounded reasoning reward improves the two-stage planner-executor system over execution-only training, suggesting that reasoning supervision should evaluate not only whether a trace looks good, but also whether it helps the model that consumes it. Our code is available at: https://github.com/MasaiahHan/TraceLift

Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relative Policy Optimization suffer from coarse grained, sequence level credit assignment, which severely struggles to isolate pivotal reasoning steps within long Chain of Thought generations. Furthermore, the standard unbounded Kullback Leibler divergence penalty induces severe gradient instability and mode seeking conservatism, ultimately stifling the discovery of novel reasoning trajectories. To overcome these limitations, we introduce Distribution Guided Policy Optimization, a novel critic free reinforcement learning framework that reinterprets distribution deviation as a guiding signal rather than a rigid penalty. DGPO replaces the volatile KL divergence with the bounded Hellinger distance to safely quantify token level exploration without the risk of gradient explosion. To effectively distinguish genuine reasoning breakthroughs from hallucinatory noise, we propose an entropy gating mechanism that scales this deviation by the policy`s epistemic uncertainty. By dynamically redistributing the coarse sequence-level advantage to individual tokens based on these gated scores, DGPO heavily incentivizes critical exploratory steps while suppressing unwarranted, low-entropy deviations. Consequently, DGPO completely eliminates the traditional token-level KL penalty and achieves fine-grained credit reallocation without the computational overhead of an additional value network. Extensive empirical evaluations demonstrate that DGPO sets a new state-of-the-art for critic free alignment. Notably, on the Qwen2.5-32B architecture, DGPO achieves 60.0% Avg@32 accuracy and 46.0% Avg@32 accuracy on the challenging AIME2024 and AIME2025 benchmarks respectively, substantially outperforming competitive baselines like DAPO.

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards provide limited guidance for assigning credit to individual steps within long interaction trajectories. Existing approaches often introduce dense intermediate supervision, such as process reward models or auxiliary self-supervised signals, which increases supervision and tuning complexity and may limit generalization across tasks and domains. We present AEM, a supervision-free credit assignment method that adaptively modulates entropy dynamics during RL training to improve the exploration-exploitation trade-off. Since in agentic RL the environment is typically affected by a complete response, rather than an individual token, our analysis lifts entropy dynamics from the token level to the response level, aligning uncertainty estimation with the effective action granularity of LLM agents and reducing sensitivity to token-level sampling noise. We further show that entropy drift under natural-gradient updates is governed by the interaction between the sampled-response advantage and its relative surprisal. Motivated by this result, AEM derives a practical response-level uncertainty proxy and uses it to rescale advantages, leveraging the evolving balance between positive and negative samples to naturally transition from exploration to exploitation. Extensive experiments on ALFWorld, WebShop, and SWE-bench-Verified with models ranging from 1.5B to 32B demonstrate that AEM consistently improves strong RL baselines, including a +1.4% gain when integrated into a state-of-the-art software-engineering RL training framework.

As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to complex navigation. While Reinforcement Learning (RL) has emerged as a promising paradigm for training MLLM agents on dynamic GUI tasks, its effective application faces a dilemma. Standard Offline RL often relies on static step-level data, neglecting global trajectory semantics such as task completion and execution quality. Conversely, Online RL captures the long-term dynamics but suffers from high interaction costs and potential environmental instability. To bridge this gap, we propose SOLAR-RL (Semi-Online Long-horizon Assignment Reinforcement Learning). Instead of relying solely on expensive online interactions, our framework integrates global trajectory insights directly into the offline learning process. Specifically, we reconstruct diverse rollout candidates from static data, detect the first failure point using per-step validity signals, and retroactively assign dense step-level rewards with target-aligned shaping to reflect trajectory-level execution quality, effectively simulating online feedback without interaction costs. Extensive experiments demonstrate that SOLAR-RL significantly improves long-horizon task completion rates and robustness compared to strong baselines, offering a sample-efficient solution for autonomous GUI navigation.

Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learning requires solving the credit assignment problem: determining how individual utterances contribute to multi-turn dialogue outcomes. Existing approaches directly employ language models to distribute episode-level rewards, yielding attributions that are retrospective and lack theoretical grounding. We propose SAVOIR (ShApley Value fOr SocIal RL), a novel principled framework grounded in cooperative game theory. Our approach combines two complementary principles: expected utility shifts evaluation from retrospective attribution to prospective valuation, capturing an utterance's strategic potential for enabling favorable future trajectories; Shapley values ensure fair credit distribution with axiomatic guarantees of efficiency, symmetry, and marginality. Experiments on the SOTOPIA benchmark demonstrate that SAVOIR achieves new state-of-the-art performance across all evaluation settings, with our 7B model matching or exceeding proprietary models including GPT-4o and Claude-3.5-Sonnet. Notably, even large reasoning models consistently underperform, suggesting social intelligence requires qualitatively different capabilities than analytical reasoning.

Agentic reinforcement learning (RL) is emerging as a critical post-training paradigm for improving LLM agent capabilities. Existing RL algorithms for LLMs largely follow the token-centric paradigm as in RLHF and RLVR, where tokens serve as the basic units for modeling and optimization. However, this paradigm introduces a granularity mismatch in agentic RL, as it optimizes token-level predictions while LLM agents make step-level decisions through cycles of environmental observations and actions. To bridge this gap, we propose StepPO, a step-centric paradigm for agentic RL via step-aligned policy optimization. Specifically, we reformulate agentic RL from a token-level Markov Decision Process (MDP) into a step-level MDP, where interaction steps serve as the basic trajectory representations. We further propose step-level credit assignment to align policy optimization with the natural granularity of agent decisions. Together, StepPO optimizes agent policies at the step level for multi-turn agent-environment interaction. Experiments across multi-hop QA, academic paper search, and text-world action tasks show that StepPO consistently outperforms various RL algorithms. Further analyses provide insights into how step-centric paradigm improves agent training. We hope this step-centric paradigm offers a useful lens for understanding agent behavior and a practical path for training more capable LLM agents.

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across all intermediate decisions. This leads to high gradient variance, unstable training, and many ineffective updates, ultimately limiting sustained model improvement. We propose a counterfactual-comparison framework for credit assignment. For each input, the framework samples multiple reasoning trajectories and treats their differences as implicit approximations to alternative decisions. This yields an implicit process-level advantage estimator that converts sparse terminal rewards into step-sensitive learning signals. Building on this framework, we introduce Implicit Behavior Policy Optimization (IBPO), which substantially improves training stability and the performance ceiling on mathematical and code-reasoning benchmarks. Our results point to a promising direction for unlocking the reasoning potential of LLMs.

State-of-the-art reasoning models utilize long chain-of-thought (CoT) to solve increasingly complex problems using more test-time computation. In this work, we explore a long CoT setting where the model makes up to K successive attempts at solving a problem, in which each attempt is allowed to build on earlier ones after the model receives a hard verifier feedback. This motivates RL methods that can harness per-attempt rewards by carefully weighting individual attempts. We study optimizing the Verification@K reward (the model succeeds by the K-th attempt) and show that naively weighing the attempts by their pass/fail results in biased gradients. We introduce Calibrated Attempt-Level (CAL) GRPO by devising a weighing strategy to obtain unbiased gradients while maintaining small variance. Our theory reveals how incorporating per-attempt rewards influence the training and the eventual Verification@K performance. Experiments, baselines, and ablations on synthetic and real data corroborate our theory and the benefits of CAL-GRPO over vanilla GRPO as well as naive weighting.

In cooperative teams where agents act in a fixed order and share a single team-level reward (multi-agent language systems, sequential robotic tasks), per-agent credit assignment is under-determined. Critic-based approaches scale poorly as the number of agents grows owing to the costly maintenance of joint/factored critic(s), whereas the existing critic-free alternatives have other issues: common credit across agents that couples every agent's signal to teammate noise, importance-sampling corrections for upstream-update staleness that incur variance exponential in team size, or per-agent counterfactual replay that isolates each agent's effect at the price of extra environment or reward calls. We propose COSAC, a critic-free per-agent policy gradient for sequential cooperative teams. COSAC fits an additive per-agent decomposition of the team reward by a single ridge regression on the rollout batch (giving each agent a learning signal decoupled from teammate noise), and computes each agent's counterfactual advantage from fictitious continuations of the current policy (policy forward passes that replace both importance-sampling reweighting and per-agent environment replay, at no extra environment or reward cost). The estimator instantiates the Sequential Aristocrat Utility (SeqAU), our extension of Wolpert and Tumer's (2001) aristocrat utility to sequential teams. We prove bias and variance bounds on SeqAU credits that stay controlled as the team grows. Our controlled study on sequential bandits demonstrates that COSAC attains the lowest advantage MSE and consistently low learning regret across team sizes up to $K = 16$. On the AI2 Reasoning Challenge (ARC) task, where four Qwen3-0.6B agents reason in turn about a grade-school science question, COSAC attains faster convergence than the other critic-free baselines.

The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provided only at the end of a sequence into fine-grained learning signals that can guide intermediate reasoning steps. Existing approaches either rely on outcome-level rewards for sequence-level optimization, which makes precise credit assignment difficult, or depend on externally constructed process supervision, which is costly and difficult to scale sustainably. To address this, we propose a new perspective: reinforcement learning for reasoning can be understood as the problem of internalizing outcome supervision into process supervision. From this perspective, we introduce a supervision-internalization method for reinforcement learning for reasoning, enabling the model to automatically extract process-level learning signals through identifying, correcting, and reusing failed reasoning trajectories, thereby achieving finer-grained policy optimization under outcome-only supervision. We further abstract this idea into a new training paradigm, in which the model continually generates and refines its own internal process supervision during reinforcement learning, opening a new path for fine-grained credit assignment in reinforcement learning for reasoning that differs from externally provided process supervision.

Reinforcement learning has emerged as an effective paradigm for training large language models to perform search-augmented reasoning. However, existing approaches rely on trajectory-level rewards that cannot distinguish precise search queries from vague or redundant ones within a rollout group, and collapse to a near-zero gradient signal whenever every sampled trajectory fails. In this paper, we propose IG-Search, a reinforcement learning framework that introduces a step-level reward based on Information Gain (IG). For each search step, IG measures how much the retrieved documents improve the model's confidence in the gold answer relative to a counterfactual baseline of random documents, thereby reflecting the effectiveness of the underlying search query. This signal is fed back to the corresponding search-query tokens via per-token advantage modulation in GRPO, enabling fine-grained, step-level credit assignment within a rollout. Unlike prior step-level methods that require either externally annotated intermediate supervision or shared environment states across trajectories, IG-Search derives its signals from the policy's own generation probabilities, requiring no intermediate annotations beyond standard question-answer pairs. Experiments on seven single-hop and multi-hop QA benchmarks demonstrate that IG-Search achieves an average EM of 0.430 with Qwen2.5-3B, outperforming the strongest trajectory-level baseline (MR-Search) by 1.6 points and the step-level method GiGPO by 0.9 points on average across benchmarks, with particularly pronounced gains on multi-hop reasoning tasks. Despite introducing a dense step-level signal, IG-Search adds only ~6.4% to per-step training wall-clock time over the trajectory-level baseline and leaves inference latency unchanged, while still providing a meaningful gradient signal even when every sampled trajectory answers incorrectly.

Temporal credit assignment in reinforcement learning is often approached by introducing value estimates at multiple discount factors. A natural next step is to let the actor dynamically route among these temporal heads, using either differentiable attention or heuristic uncertainty weights. This paper argues that such routing can create a numerical shortcut rather than a reliable temporal abstraction. We study this issue in a controlled PPO setting on LunarLander-v2, using the environment as a visual sandbox for diagnosing failure modes. First, we formalize Surrogate Objective Hacking: a differentiable softmax router exposed to the PPO surrogate receives a direct gradient toward advantage heads that are numerically favorable for the current update, even when this routing change does not correspond to improved physical control. Because unnormalized advantages at different discount factors have different effective scales, this creates a scale-discrepancy vulnerability. Second, we identify the Paradox of Temporal Uncertainty in gradient-free error-based routing: short-horizon heads can receive the largest routing share because their prediction targets are easier, even when they are less aligned with delayed task success. As a structural response, we study Target Decoupling: the critic may retain multi-timescale auxiliary heads, but the actor is updated only with the long-horizon advantage. Target Decoupling is not presented as a broad performance booster; in this run set it removes the exploitable actor-side routing pathway and improves the observed worst-seed return. Code is available at https://github.com/ben-dlwlrma/Representation-Over-Routing.

Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained advantage estimation based on a learned value function. However, learned value models are often avoided in modern large language model (LLM) RL because conventional discriminative critics are difficult to train reliably. We revisit value modeling and argue that this difficulty is partly due to limited expressiveness. In particular, representation complexity theory suggests that value functions can be hard to approximate under the one-shot prediction paradigm used by existing value models, and our scaling experiments show that such critics do not improve reliably with scale. Motivated by this observation, we propose Generative Actor-Critic (GenAC), which replaces one-shot scalar value prediction with a generative critic that performs chain-of-thought reasoning before producing a value estimate. We further introduce In-Context Conditioning, which helps the critic remain calibrated to the current actor throughout training. GenAC improves value approximation, ranking reliability, and out-of-distribution generalization, and these gains translate into stronger downstream RL performance than both value-based and value-free baselines. Overall, our results suggest that stronger value modeling is a promising direction for improving credit assignment in LLM reinforcement learning.

Reinforcement learning (RL) for large language models (LLMs) increasingly relies on sparse outcome rewards, yet such rewards say little about which token, reasoning step, tool call, memory operation, or agent caused an outcome. This credit assignment (CA) problem spans reasoning RL and becomes sharper in agentic RL, where environment interaction introduces transition non-closure, partial observability, limited replay, heterogeneous actions, weak intermediate verifiability, and agent coupling. We synthesize a unified corpus of 69 papers published from January 2024 through July 31, 2026: 56 core CA methods and 13 adjacent or boundary enablers, selected from 92 deduplicated screening records. We retain the original granularity-by-methodology taxonomy and add a six-diagnostic framework mapping assumption breaks to identification barriers, estimators, and evaluation controls. A source-located full-text audit covers a fixed 42-core-paper subset. Two algorithm researchers independently and blindly cross-coded 252 diagnostic cells, agreeing on 223 (88.5%); per-diagnostic Cohen's kappa ranges from .543 to .909, and principal-family agreement is 42/42 (kappa=1.000). Beyond taxonomy, we establish when restored-state comparisons identify a protocol-specific causal contrast, show that text-only histories can leave even the sign of credit unidentified, and introduce a reusable CA-ID Card linking each claim to its estimand, evidence provenance, and falsification test. An atomic reporting audit describes comparator, budget parity, ablation, overhead, uncertainty, and replay coverage without constructing a cross-paper leaderboard. The companion repository hosts a living catalog and decision aids; a dated release of the frozen audit bundle is planned there separately from the minimal arXiv source.

Learning high-performance control policies that remain consistent with expert behavior is a fundamental challenge in robotics. Reinforcement learning can discover high-performing strategies but often departs from desirable human behavior, whereas imitation learning is limited by demonstration quality and struggles to improve beyond expert data. We propose a behavior-constrained reinforcement learning framework that improves beyond demonstrations while explicitly controlling deviation from expert behavior. Because expert-consistent behavior in dynamic control is inherently trajectory-level, we introduce a receding-horizon predictive mechanism that models short-term future trajectories and provides look-ahead rewards during training. To account for the natural variability of human behavior under disturbances and changing conditions, we further condition the policy on reference trajectories, allowing it to represent a distribution of expert-consistent behaviors rather than a single deterministic target. Empirically, we evaluate the approach in high-fidelity race car simulation using data from professional drivers, a domain characterized by extreme dynamics and narrow performance margins. The learned policies achieve competitive lap times while maintaining close alignment with expert driving behavior, outperforming baseline methods in both performance and imitation quality. Beyond standard benchmarks, we conduct human-grounded evaluation in a driver-in-the-loop simulator and show that the learned policies reproduce setup-dependent driving characteristics consistent with the feedback of top-class professional race drivers. These results demonstrate that our method enables learning high-performance control policies that are both optimal and behavior-consistent, and can serve as reliable surrogates for human decision-making in complex control systems.

In user-agent interaction scenarios such as recommendation, brainstorming, and code suggestion, Large Language Models (LLMs) often generate sets of candidate recommendations where the objective is to maximize the collective utility of the entire set rather than individual candidates independently. However, existing reinforcement learning post-training paradigms, such as Group Relative Policy Optimization (GRPO), typically assign the same set-level scalar reward to every candidate in the set. This leads to noisy training signals where poor candidates free-ride on the high reward produced by a single strong peer, resulting in suboptimal exploration. To address this, we propose Shapley-Enhanced GRPO (ShapE-GRPO). By leveraging the permutation-invariant nature of set-level utility, we derive a Shapley-enhanced formulation from cooperative game theory to decompose set-level rewards into granular, candidate-specific signals. We show that our formulation preserves the fundamental axioms of the Shapley value while remaining computationally efficient with polynomial-time complexity. Empirically, ShapE-GRPO consistently outperforms standard GRPO across diverse datasets with accelerated convergence during training.