collaborators

15 papers

cs.CR2026

Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models

Zhang Wei, Hanxuan Chen, Peilu Hu +19

Red-teaming is becoming a central part of large language model (LLM) safety evaluation, yet current practice still relies heavily on expert-written prompts or fixed benchmark suite…

cs.LG2026

Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning

Haiwen Yi, Xinyuan Song

Large language model (LLM) agents are usually improved by changing prompts, models, or hand-written workflows, while the execution harness around the model is treated as fixed infr…

cs.AI2026

Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents

Haiwen Yi, Xinyuan Song

Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees, which actions it can take,…

cs.AI2026

Repair the Amplifier, Not the Symptom: Stable World-Model Correction for Agent Rollouts

Xinyuan Song, Zekun Cai

Long-horizon language agents increasingly maintain executable world models in the form of planning graphs, where tool calls, validators, memory updates, recovery branches, and fina…

cs.AI2026

Ask the World Before Acting: Environment Probing for Calibrated Agent World Models

Xinyuan Song, Zekun Cai

Language agents acting over long horizons must maintain beliefs about tool states, object locations, graph edges, and subgoal dependencies. When these beliefs drift, failures can b…

cs.AI2026

Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents

Xinyuan Song, Zekun Cai

Language agents plan by generating not only actions but also implicit predictions of how the world will change. These imagined state updates make agents flexible, but they also cre…