SwarmSafe-Delta: Isolating Message Effects on LLM Agent Safety
cs.MA, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Comments: 10 pages, 3 figures, 3 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- ACIArena: Toward Unified Evaluation for Agent Cascading Injection
- REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- Counterfactual Graph for Multi-Agent LLM Calibration
- TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems
- Towards a Science of Scaling Agent Systems
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
- SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks
- When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents
- Auditing Agent Harness Safety
- Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures
- Towards Understanding Sycophancy in Language Models
- Learning When to Trust via Selective Context Preference Optimization
- A Survey on Large Language Model based Autonomous Agents
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Related papers
- MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
- Iterative Negotiation and Oversight: A Case Study in Decentralized Air Traffic Management
- Towards using Large Language Models for Risk Negotiation and Consensus-building in One Health contexts
- A-MapReduce: Executing Wide Search via Agentic MapReduce
- AgentCue: Statistical Summaries for Guiding Decentralized Multi-Agent Self-Organization
- Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning