collaborators

14 papers

cs.AI2026

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

Wanying Qu, Qinghua Mao, Yu Li +12

The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime contro…

cs.AI2026

Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning

Yijin Zhou, Linqian Zeng, Xiaoya Lu +4

Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate erro…

cs.AI2026

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

Tianyi Zhou, Dongrui Liu, Leitao Yuan +2

LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and interaction style. Building su…

cs.AI2026

ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis

Yu Li, Haoyu Luo, Yuejin Xie +10

Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or…

cs.AI2026

Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence

Xinquan Chen, Zhenyun Yin, Shan He +38

As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment intera…

cs.AI2026

Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex

Zhonghao Yang, Yu Li, Yanxu Zhu +6

As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse…