arXiv AI
ProcessLight: Process Supervision for Large Language Model Based Traffic Signal Control
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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 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 AI
3d ago
Learning Process Rewards via Reasoning State Propagation
The paper introduces Reasoning State Propagation (RSP), a method that models each reasoning prefix with a binary validity state and learns transitions between successive states. RSP predicts break and repair probabilities to connect intermediate reasoning states to the final outcome, enabling outcome supervision to guide learning of earlier steps. Experiments on reasoning search, response selection, and reinforcement learning show RSP consistently outperforms existing Process Reward Models, achieving notable gains over Qwen2.5-Math-PRM.
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.
arXiv Computation and Language
Sep 22
Rubric-Guided Process Reward for Stepwise Model Routing
arXiv:2605.29310v2 Announce Type: replace-cross Abstract: Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent...
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.