conftrace_

self-critique mechanism

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

executable verification (1) tree-structured search (1) on-policy reinforcement learning (1) runtime feedback (1) intermediate step (1) language model (1) reward hacking (1) distribution shift (1) monte carlo sampling (1) code generation (1)

Papers

Fixing Distribution Shifts of LLM Self-Critique via On-Policy Self-Play Training ACL 2025 Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation ICML 2025