3 papers
cs.AI2026
CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
Qijia He, Jiayi Cheng, Chenqian Le +8
Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect answer. Existing cost-aware system…
cs.CL2026
PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents
Zhenbang Du, Jun Luo, Zhiwei Zheng +8
Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns. Post-training such agents is challenging, as reinforcement learning…
cs.AI2025
Rethinking Human Preference Evaluation of LLM Rationales
Ziang Li, Manasi Ganti, Zixian Ma +3
Large language models (LLMs) often generate natural language rationales -- free-form explanations that help improve performance on complex reasoning tasks and enhance interpretabil…