conftrace_

step-level reward

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

process reward model (3) mathematical reasoning (2) self-supervised autoencoder (1) contrastive pointwise mutual information (1) symbolic computer vision (1) geometric diagram reconstruction (1) reasoning quality (1) large language model (1) agent training (1) group relative policy optimization (1)

Papers

Efficient Process Reward Modeling via Contrastive Mutual Information ACL 2026 Hierarchical Process Reward Models are Symbolic Vision Learners CVPR 2026 Step-GRPO: Enhancing Reasoning Quality and Efficiency via Structured PRM-Based Reinforcement Learning AAAI 2026 Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement EMNLP 2024