AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions

Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani, Jun Liu

ECCV 2026 · Multi-agent systems and games › LLM agents · approach: Agent safety and attack benchmarks · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace original agent selection with FJ-based strategyMCA · MMLU, SelfCheckGPTDelta Acc: 2.6% -> 28.7%Improved
replace original agent selection with FJ-based strategyMAD-Spear · MMLU, SelfCheckGPTDelta Acc: 6.9% -> 43.5%Improved
replace original agent selection with FJ-based strategyMCA · MMMU, SelfCheckGPTDelta Acc: 4.1% -> 32.6%Improved
replace original agent selection with FJ-based strategyMAD-Spear · MMMU, SelfCheckGPTDelta Acc: 7.6% -> 45.3%Improved
add stealth-oriented prompt modifications to MAD-SpearMAD-Spear · MMLU, SelfCheckGPTDelta Acc: detection rate 97.8% -> 6.7%; Delta Acc 1.5% -> 6.9%Mixed
add stealth-oriented prompt modifications to MCAMCA · MMLU, SelfCheckGPTDelta Acc: detection rate 95.1% -> 4.5%; Delta Acc 0.7% -> 2.6%Mixed
compare best heuristic Variant III with our strategyMAD-Spear · MMLU, SelfCheckGPTDelta Acc: 21.8% -> 43.5%Improved
add stubborn-broadcaster modification (1) to FJ formulation (ablation)MAD-Spear · MMMU, SelfCheckGPTDelta Acc: 40.2% -> 45.3%Improved
add selective-influence modification (2) to FJ formulation (ablation)MAD-Spear · MMMU, SelfCheckGPTDelta Acc: 35.1% -> 45.3%Improved
add both modifications to standard FJ model (ablation)MAD-Spear · MMMU, SelfCheckGPTDelta Acc: 25.7% -> 45.3%Improved
add both modifications to standard FJ model (ablation)MAD-Spear · MMMU, G-SafeguardDelta Acc: 22.2% -> 42.2%Improved
add dedicated solver vs naive enumerationformulation solver · solving timeDelta Acc: practically infeasible -> 0.54 sImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy