Trajectory Unlearning on LLM-based Agents
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
- Tool Unlearning for Tool-Augmented LLMs
- Who's Harry Potter? Approximate Unlearning in LLMs
- Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
- BraveGuard: From Open-World Threats to Safer Computer-Use Agents
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
- AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Agentic Unlearning: When LLM Agent Meets Machine Unlearning
- SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- Qwen2.5 Technical Report
- Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents
- Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
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