6 papers
Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments
Xiaoyang Yuan, Ji Zhao, Xingyu Hu +7
Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were achieved. Scaling either trajector…
DAAF: From Failure Localization to Editable System Assets in LLM Agents
Xiaoyang Yuan, Qi Liu, Yubin Ruan +9
Deployed LLM agents increasingly rely on persistent, versioned system assets such as routing rules, knowledge segments, prompt instructions, and reusable skills. Failure-localizati…
Terminal Agents: A Survey of AI Agents in Command-Line Environments
Yi Bin, Xiaoyang Yuan, Haoxi Zeng +9
Large language model agents increasingly act through terminals, yet existing surveys disperse terminal-mediated behavior across software engineering, tool use, and computer-use res…
MAP-Law: Coverage-Driven Retrieval Control for Multi-Turn Legal Consultation
Qinchuan Cheng, Jiaqi Liu, Ruixuan Xie +2
Legal consultation is inherently iterative: before giving advice, a system must identify relevant legal elements, gather missing facts and authorities, and determine whether the cu…
RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering
Wencheng Ye, Xiaoyang Yuan, Yi Bin +4
Recent work on domain-specific reasoning with large language models (LLMs) often relies on training-intensive approaches that require parameter updates. While activation steering h…
More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration
Xiaoyang Yuan, Yujuan Ding, Yi Bin +5
Reinforcement Learning with Verifiable Rewards (RLVR) is a promising paradigm for enhancing the reasoning ability in Large Language Models (LLMs). However, prevailing methods prima…