Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
cs.AI, cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Sources
- Scaling Laws for Neural Language Models
- On the Opportunities and Risks of Foundation Models
- Reset-Free Lifelong Learning with Skill-Space Planning
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
- Agent Workflow Memory
- Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents
- Belief Memory: Agent Memory Under Partial Observability
- Concrete Problems in AI Safety
- A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
- Language Models (Mostly) Know What They Know
- A Survey on the Honesty of Large Language Models
- An Explanation of In-context Learning as Implicit Bayesian Inference
- Effects of Treatment on the Treated: Identification and Generalization
- Representation Engineering: A Top-Down Approach to AI Transparency
- Steering Language Models With Activation Engineering
- ReAct: Synergizing Reasoning and Acting in Language Models
- Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
- MemGPT: Towards LLMs as Operating Systems
- AgentRefine: Enhancing Agent Generalization through Refinement Tuning
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