arXiv AI
Process Advantage Signal Shaping: Advantage Construction for Process-Supervised Reinforcement Learning in LLM Reasoners
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 30
Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners
arXiv:2606. 29296v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a default recipe for process-supervised reinforcement learning of LLM reasoners, and dense process supervision -- via learned process reward models (PRMs) or on-policy-distillation KL signals -- is a common way to densify its otherwise weak outcome reward.
arXiv AI
Jun 2
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
arXiv:2604. 10688v2 Announce Type: replace-cross Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult.
arXiv AI
Sep 30
SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation
SIPO (Self‑Instructing Policy Optimization) unifies reinforcement learning with on‑policy self‑distillation by using a contrastive self‑teacher to generate token‑level credit signals. The method samples multiple rollouts per prompt, pairs each with a reference answer and its mistakes, and uses the difference in teacher log‑probabilities to provide dense feedback while still respecting the overall task reward. Experiments on reasoning and code‑generation benchmarks show that SIPO outperforms both RLVR and OPSD baselines without requiring an external teacher or extra generation steps.
arXiv AI
Aug 14
Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
arXiv AI
Sep 28
Stepwise Intrinsic Rewards for Reasoning in Large Language Models
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.
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.