Auditing Agent Actions through Query-Conditioned Attribution
cs.AI, cs.CL
Submitted: 2026-09-27
Updated: 2026-09-29
Terminology
Sources
- AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework
- TRAIL: Trace Reasoning and Agentic Issue Localization
- Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
- Auditable Agents
- The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
- Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks
- Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
- ReAct: Synergizing Reasoning and Acting in Language Models
- Where LLM Agents Fail and How They can Learn From Failures
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