arXiv AI
Aug 3
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
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.
Related stories
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
Aug 10
Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents
arXiv:2608. 06861v1 Announce Type: new Abstract: Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions.
arXiv AI
Sep 1
ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground Truth
arXiv:2512.03244v2 Announce Type: replace-cross Abstract: Training process reward models (PRMs) requires step-level correctness labels, obtained either through expensive human annotation or by relyin...
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 AI
Sep 1
Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide
arXiv:2608.30051v1 Announce Type: new Abstract: Process reward models (PRMs) provide dense step-level guidance for search-based reasoning, enabling inference-time compute to be allocated toward promi...
arXiv Machine Learning
Aug 4
Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning
arXiv:2608. 01418v1 Announce Type: cross Abstract: Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models.
arXiv AI
Jul 29
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
arXiv:2607. 25659v1 Announce Type: new Abstract: Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria.
arXiv AI
Aug 7
DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
arXiv:2608. 06243v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals are typically sparse and at the sequence-level.
arXiv Machine Learning
Sep 3
Cliff: Learning Process Rewards from the First Mistake
Cliff is a reward‑shaping method for reinforcement learning with verifiable rewards that identifies the first mistake in a language model’s reasoning process using an off‑the‑shelf teacher. By splitting each rollout into a correct prefix and an incorrect suffix, Cliff assigns token‑level advantages—positive for correct tokens and negative for the rest—providing fine‑grained supervision. Across 12 scenarios, Cliff outperforms on‑policy distillation by 15% and standard GRPO by 7%, even when the teacher is only modestly capable.
arXiv AI
Jun 9
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
arXiv:2603. 25184v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks.
arXiv AI
Jun 18
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
arXiv:2606. 18810v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps.