arXiv AI
Jun 11
ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.
RAWR: Reward Assignment Without Rollouts in Verifiable Domains
Related stories
arXiv AI
3d ago
Inducing Process Supervision from Outcome-Only Reinforcement Learning
arXiv:2609.36641v1 Announce Type: cross Abstract: Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning....
arXiv Machine Learning
Jun 9
The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning
arXiv:2606. 09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.
arXiv AI
Jun 6
Controllable and Verifiable Process Data Synthesis for Process Reward Models
arXiv:2605. 02395v2 Announce Type: replace Abstract: Process reward models (PRMs) rely on high-quality process supervision data, yet existing construction methods often provide limited control over error location, error type, and trajectory consistency.
arXiv AI
Sep 21
LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers
arXiv:2609.21492v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has been shown to improve the performance of large language models (LLMs), yet existing optimization methods largely r...
arXiv Machine Learning
Sep 4
Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning
The paper investigates whether the text of chain‑of‑thought reasoning steps actually reflects their true importance for a model’s final answer. By defining step importance as the advantage in expected reward when a step is included, the authors use Monte Carlo rollouts to estimate ground truth and then test whether large language model judges can identify high‑advantage steps. They find that capable LLMs can beat a prevalence baseline but still fall far short of a noise ceiling, and that fine‑tuning a step‑level critic improves detection for incorrect responses but remains distant from the ceiling for correct ones, indicating that step importance is only partially recoverable from the reasoning trace text.
arXiv AI
Jul 15
Rethinking Reward Models for Multi-Domain Test-Time Scaling
arXiv:2510. 00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic.
arXiv AI
Aug 7
Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.
arXiv Machine Learning
Sep 24
Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning
The paper introduces RECAP, a redundancy-aware credit assignment method that improves reasoning efficiency in large language models by assigning credit to each reasoning step based on its downstream role and contribution to the correct answer. RECAP uses a semantic dependency graph to measure structural responsibility and evaluates step efficacy via changes in gold-answer log-likelihood, enabling step-specific updates without requiring a separate reward model or concise trajectories. Experiments on two 7B models across four mathematical reasoning benchmarks show that RECAP enhances the accuracy-efficiency trade-off, boosting pass@1 by 2.0–3.7 percentage points while cutting reasoning tokens by 8–31% compared to GRPO.
arXiv AI
2d ago
LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models
The paper introduces LSR‑Ben, a benchmark designed to evaluate process reward models (PRMs) on scientific and logical reasoning tasks, addressing a gap left by existing math‑focused benchmarks. Experiments on 22 models reveal that PRMs and LLMs perform poorly in non‑mathematical domains, with LLMs tending to over‑identify errors while PRMs tend to overlook them. LSR‑Ben aims to spur research that broadens PRM applicability and improves LLM reasoning.
arXiv Machine Learning
Jun 15
Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards
arXiv:2505. 04671v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) trained with reinforcement learning (RL) have improved Text-to-SQL performance.
arXiv Machine Learning
Jun 29
The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment
arXiv:2606. 27739v1 Announce Type: new Abstract: Process reward models (PRMs) enhance the reasoning capabilities of large language models (LLMs) by providing fine-grained feedback, yet training PRMs typically requires expensive stepwise annotations.