ReplayLens: Auditing Agents' Use of Outcomes
cs.AI, cs.LG, cs.MA
Submitted: 2026-09-28
Updated: 2026-10-03
Sources
- MemFail: Stress-Testing Failure Modes of LLM Memory Systems
- Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit
- AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
- REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
- MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery
- Locating and Editing Factual Associations in GPT
- Counterfactual Credit Assignment in Model-Free Reinforcement Learning
- Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures
- Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
- HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents
- Deep Sets
- Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay
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
- Agents' Last Exam
- 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