1
The Bidirectional Process Reward Model
提出双向过程奖励模型，突破传统单向奖励局限，提升语言模型推理与对齐性能。
arXiv:2508.01682v3 Announce Type: replace Abstract: Process Reward Models (PRMs), which assign fine-grained scores to intermediate reasoning steps wit…
2
SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution
打破验证黑箱，SEVA用过程奖励让大模型幻觉可追溯、可自纠。
arXiv:2606.29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are…
3
Process-Reward Tactic Evolution for Long-Horizon Bioinformatics Workflows
让AI在长流程生物信息学任务中自我优化，过程奖励策略进化出更稳的决策路径。
arXiv:2606.20839v1 Announce Type: new Abstract: LLM agents can write code and call tools, but reliable bioinformatics work requires long-horizon inter…
4
VeriBound: PAC-Bayesian Generalization Bounds for Process Reward Models Trained with Formal Verification Tools
将形式化验证与PAC-Bayesian理论结合，为过程奖励模型提供可证实的泛化边界，是AI安全领域的硬核进展。
arXiv:2606.20740v1 Announce Type: cross Abstract: Process Reward Models (PRMs) provide step-level verification for Large Language Model (LLM) reasonin…
5
StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis
逐步过程奖励引导LLM微调，提升RTL合成质量的创新方法
arXiv:2606.04246v1 Announce Type: new Abstract: Automatic generation of RTL code for digital hardware designs remains challenging due to long-horizon …
6
ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents
提出ARBOR框架，用可复用评分缓冲为搜索代理提供在线过程奖励，显著提升推理与搜索效率。
arXiv:2606.03239v1 Announce Type: new Abstract: LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process…
7
Verifiable Process Rewards for Agentic Reasoning
提出可验证过程奖励机制，让智能体推理更可信可解释，强化学习新思路。
arXiv:2605.10325v2 Announce Type: replace Abstract: Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of larg…
8
Understanding and Mitigating Premature Confidence for Better LLM Reasoning
最新研究揭示LLM长思维链中“过早自信”导致的逻辑缺口，并提出基于过程奖励模型的缓解策略，提升推理质量。
arXiv:2605.24396v1 Announce Type: new Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustif…
9
VRPRM: Process Reward Modeling via Visual Reasoning
通过视觉推理提升过程奖励建模精度，为复杂任务训练提供新思路。
arXiv:2508.03556v3 Announce Type: replace Abstract: Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) becau…
10
rePIRL: Learn PRM with Inverse RL for LLM Reasoning
用逆强化学习从推理轨迹中自动学习过程奖励模型，有效提升大语言模型的复杂推理能力。
arXiv:2602.07832v2 Announce Type: replace Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficienc…
11
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
超越正确性：通过强化学习调和过程与结果奖励，为模型训练提供新视角
arXiv:2509.03403v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning …