Skip to content
conftrace_

outcome supervision

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

process supervision (5) reinforcement learning (3) large language model (2) demonstrations (1) reverse curriculum reinforcement learning (1) change of trajectory measure lemma (1) statistical difficulty (1) dynamic knowledge (1) advantage function (1) model memorization (1)

Papers

Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision EMNLP 2025 Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective ICML 2025 Process-Supervised Reinforcement Learning for Code Generation EMNLP 2025 Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning EMNLP 2025 Let's Verify Step by Step ICLR 2024 Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning ICML 2024