Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

• URL: http://arxiv.org/abs/2605.16302v1
• Date: Mon, 20 Apr 2026 13:33:54 GMT
• Title: Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
• Abstract summary: Reinforcement learning for multi-step reasoning with large language models (LLMs) often relies on sparse terminal rewards.<n>We introduce a counterfactual comparison-based credit assignment framework, which samples multiple reasoning trajectories under the same input.<n>We construct an implicit process-level advantage estimator that transforms sparse terminal rewards into step-sensitive learning signals.
• Score: 11.514388061694268
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reinforcement learning for multi-step reasoning with large language models (LLMs) often relies on sparse terminal rewards, leading to poor credit assignment conditions where the final feedback is evenly propagated across all intermediate decisions. This results in high gradient variance, unstable training, and numerous ineffective updates, ultimately causing the model to fail and preventing sustained improvement. We introduce a counterfactual comparison-based credit assignment framework, which samples multiple reasoning trajectories under the same input. By treating their differences as an implicit approximation of alternative decisions, we construct an implicit process-level advantage estimator that transforms sparse terminal rewards into step-sensitive learning signals. Based on this, we propose Implicit Behavior Policy Optimization (IBPO), which significantly improves training stability and performance upper bounds on mathematical and code reasoning benchmarks, pointing to a promising direction for unlocking the performance potential of LLMs.

Related papers

• Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization [31.547614109943158]
  Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for eliciting long-chain reasoning in large language models.<n>We propose ISPO (Intrinsic Signal Policy Optimization), which combines a sequence-level signal measuring how informative the thinking trajectory is for the final answer, with a token-level directional reward whose hallucinated-certainty hinge penalizes confidently-wrong predictions at critical decision tokens.<n>ISPO consistently outperforms competitive baselines, with the largest gains on the hardest benchmarks where zero-advantage collapse is most frequent, and training-dynamics diagnostics confirm that both failure modes are decreased.
  arXiv  Detail & Related papers  (2026-06-07T20:08:36Z)
• STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning [80.78140312980484]
  We propose language-driven stepwise trajectory redirection, termed as STRIDE.<n>We co-train a generator and a generative verifier using only outcome-based rewards, eliminating external annotations.<n> Experiments on diverse reasoning benchmarks show that STRIDE significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-13T11:04:31Z)
• Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration [22.269718913202595]
  We introduce Contextual Counterfactual Credit Assignment (textbftextttC3)<n>Instead of distributing rewards across an entire episode, textbftextttC3 isolates the causal impact of individual messages.<n>textbftextttC3 improves terminal performance over established baselines.
  arXiv  Detail & Related papers  (2026-03-06T20:25:11Z)
• DiffuReason: Bridging Latent Reasoning and Generative Refinement for Sequential Recommendation [20.756497463882763]
  We propose DiffuReason, a unified "Think-then-Diffuse" framework for sequential recommendation.<n>It integrates multi-step Thinking Tokens for latent reasoning, diffusion-based refinement for denoising intermediate representations, and end-to-end Group Relative Policy Optimization.<n>Experiments on four benchmarks demonstrate that DiffuReason consistently improves diverse backbone architectures.
  arXiv  Detail & Related papers  (2026-02-10T12:55:30Z)
• Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training [29.56905427210088]
  gradient-ARM is a framework that jointly optimize a rubric generator and a judge using reinforcement learning from preference feedback.<n>We show that gradient-ARM achieves state-of-the-art performance among baselines on benchmarks and significantly improves downstream policy alignment in both offline and online reinforcement learning settings.
  arXiv  Detail & Related papers  (2026-02-02T00:50:53Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Arbitrage: Efficient Reasoning via Advantage-Aware Speculation [71.45710345765528]
  Speculative Decoding accelerates inference by employing a fast but inaccurate draft model to autoregressively propose tokens.<n>But due to unnecessary rejections caused by token mismatches in semantically equivalent steps, traditional token-level Speculative Decoding struggles in reasoning tasks.<n>We propose Arbitrage, a novel step-level speculative generation framework that routes generation dynamically based on the relative advantage between draft and target models.
  arXiv  Detail & Related papers  (2025-12-04T17:50:53Z)
• Rectifying LLM Thought from Lens of Optimization [48.98086817378953]
  Long chain-of-thought (CoT) prompting enables thorough exploration and deliberation.<n>Despite advances, long-CoT LLMs often exhibit suboptimal reasoning behaviors.<n>We introduce RePro, a novel approach to refine LLM reasoning during post-training.
  arXiv  Detail & Related papers  (2025-12-01T17:41:08Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models [50.84995206660551]
  We introduce Conditional advANtage estimatiON (CANON) to amplify the impact of a target metric without presuming its direction.<n>CANON based on entropy consistently outperforms prior methods on both math reasoning and high-complexity logic tasks.
  arXiv  Detail & Related papers  (2025-09-28T16:33:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.