Verifiable Process Rewards for Agentic Reasoning

arXiv:2605.10325 · cs.AI · Submitted 2026-05-11 · Read on arXiv

cs.AI

Submitted: 2026-05-11

Updated: 2026-10-12

Code: https://github.com/thu-nics/VPR

Terminology

• Agentic Reasoning — 4× in this paper · explained in 1 episode
• Verification — 4× in this paper · explained in 2 episodes
• Credit assignment — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Verifiable Process Rewards — 2× in this paper
• Verifier — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• FireAct: Toward Language Agent Fine-tuning
• Group-in-Group Policy Optimization for LLM Agent Training
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• OpenAI o1 System Card
• Adam: A Method for Stochastic Optimization
• OpenSpiel: A Framework for Reinforcement Learning in Games
• GEM: A Gym for Agentic LLMs
• Code Llama: Open Foundation Models for Code
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• Solving math word problems with process- and outcome-based feedback
• Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
• Qwen3 Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems