12 papers
Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference
Xuyan Ma, Yawen Wang, Junjie Wang +5
Platform-orchestrated agentic workflows have become a popular paradigm for developing LLM-based applications. However, their reliability remains a major challenge due to the uncert…
From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
Mengzhuo Chen, Junjie Wang, Zhe Liu +3
LLM agents increasingly rely on agent harness: the runtime infrastructure around the base model that defines execution environments, tool interfaces, context, lifecycle orchestrati…
OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
Jianming Chen, Yawen Wang, Junjie Wang +3
Tool-calling text-to-image (T2I) agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new…
Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents
Jianming Chen, Yawen Wang, Junjie Wang +4
Embodied agents in safety-critical applications such as Vision-Language Navigation (VLN) rely on multiple interdependent capabilities (e.g., perception, memory, planning, decision)…
Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
Mengzhuo Chen, Junjie Wang, Fangwen Mu +4
Failure attribution, i.e., identifying the responsible agent and decisive step of a failure, is particularly challenging in LLM-based multi-agent systems (MAS) due to their natural…
From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
Yawen Wang, Wenjie Wu, Junjie Wang +1
LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failur…