12 papers
What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents
Chenqian Le, Jiayi Cheng, Qijia He +3
Agent reinforcement learning (RL) increasingly runs through full execution harnesses, and a multi-harness recipe mixes two choices: exposing the policy to several harnesses, and co…
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
Junze Ye, Jiayi Cheng, Miao Lu +3
For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on. Pure behavioral cloning uses…
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…
PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretr…
Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +306
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…