Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Sources
- Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
- MeCo: Enhancing LLM-Empowered Multi-Robot Collaboration via Similar Task Memoization
- A Language Agent for Autonomous Driving
- Memory Poisoning Attack and Defense on Memory Based LLM-Agents
- Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
- Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
- DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs
- A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
- Detecting Language Model Attacks with Perplexity
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
- UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
- On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
- TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
- Certifying LLM Safety against Adversarial Prompting
- The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks
- A-MEM: Agentic Memory for LLM Agents
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
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