From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis
cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/SHU-XUN/CEG-Agent
Terminology
Sources
- Cascading Failure Prediction via Causal Inference
- Causal Explainability of Machine Learning in Heart Failure Prediction from Electronic Health Records
- CodeTracer: Towards Traceable Agent States
- Let's Verify Step by Step
- AgentBench: Evaluating LLMs as Agents
- Self-Refine: Iterative Refinement with Self-Feedback
- CSnake: Detecting Self-Sustaining Cascading Failure via Causal Stitching of Fault Propagations
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Reflexion: Language Agents with Verbal Reinforcement Learning
- BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
- StepMathAgent: A Step-Wise Agent for Evaluating Mathematical Processes through Tree-of-Error
- TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- WebArena: A Realistic Web Environment for Building Autonomous Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection