arXiv:2606. 09078v1 Announce Type: new Abstract: Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.
arXiv:2604. 09482v2 Announce Type: replace Abstract: Reasoning in knowledge-intensive domains remains challenging as intermediate steps are often not locally verifiable: unlike math or code, evaluating step correctness may require synthesizing clues across large external knowledge sources.
Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths. PRM guided search avoids this by scoring candidate continuations during generation, but requires a reward model trained with step-level labels.
arXiv:2606. 01682v1 Announce Type: cross Abstract: Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths.
arXiv:2606. 05464v1 Announce Type: new Abstract: Verifiable reward training has improved mathematical and coding reasoning, but these domains capture only part of step-by-step decision making.
The paper introduces the Implicit Prefix-Value Reward Model (IPVRM), which learns the probability of eventual correctness for each prefix directly from outcome labels, thereby aligning training targets with inference-time step signals via temporal-difference differences. IPVRM improves step-verification F1 on ProcessBench. Additionally, the authors propose Distribution-Level RL (DistRL), a policy optimization method that applies TD advantages to both sampled and high-probability tokens, offering dense counterfactual updates without extra rollouts, and show that DistRL consistently enhances downstream reasoning when combined with IPVRM.
arXiv:2607. 11089v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks through Chain-of-Thought (CoT) prompting.
arXiv:2509. 16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks.
The paper reports that in on‑policy distillation for large language models, reasoning performance can be improved by supervising only a tiny fraction of generated tokens—sometimes just one or two tokens per reasoning trajectory, about 0.05% of all tokens. This sparse supervision consistently matches or exceeds full‑token training across nine teacher‑student setups on mathematical reasoning, and is also validated on coding reasoning, Llama models, and PPO‑based reinforcement learning with verifiable reward. The findings suggest that effective post‑training does not require token‑intensive supervision and may align more closely with natural learning processes that focus on critical reasoning steps.
Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, these models often exhibit "computational overthinking," generating redundant reasoning steps that increase latency and cost without improving accuracy.
arXiv:2605. 07804v3 Announce Type: replace-cross Abstract: On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models.
arXiv:2606. 04579v1 Announce Type: new Abstract: While Process Reward Models (PRMs) have achieved remarkable success in mathematical reasoning, their application in complex scientific domains-such as biology, chemistry, and physics remains largely unexplored.