What May an Agent Change About Itself? A Containment Floor for Self-Configuring Agent Runtimes
cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
- Defeating Prompt Injections by Design
- Memory Injection Attacks on LLM Agents via Query-Only Interaction
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- Automated Design of Agentic Systems
- Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework
- Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
- AgentAbstain: Do LLM Agents Know When Not to Act?
- The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
- AIRGuard: Guarding Agent Actions with Runtime Authority Control
- Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents
- MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- Memory Poisoning Attack and Defense on Memory Based LLM-Agents
- The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents
- Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry Defense
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks