7 papers
CaveAgent: Transforming LLMs into Stateful Runtime Operators
Maohao Ran, Zhenglin Wan, Cooper Lin +21
LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks…
Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents
Chubin Zhang, Zhenglin Wan, Xingrui Yu +5
Tool-augmented agents are typically evaluated by their gains under reliable external feedback. Yet these gains leave open a key counterfactual: when feedback is unreliable, would t…
Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention
Chubin Zhang, Zhenglin Wan, Xingrui Yu +5
Runtime oversight for LLM agents is commonly framed as scalar risk prediction: estimate failure likelihood, confidence, or uncertainty, then intervene once the score crosses a thre…
Adversarial Dual On-Policy Distillation from Expressive Teacher
Zhenglin Wan, Jingxuan Wu, Xingrui Yu +5
Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal e…
FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
Zhenglin Wan, Jingxuan Wu, Xingrui Yu +4
Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. Howeve…
Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching
Jingxuan Wu, Zhenglin Wan, Xingrui Yu +4
Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. Existing approaches to improving divers…