AI Paper Atlas

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

Resilience in Ambient Multi-Agent LLMs via Decentralized Bio-Autonomic Control and Immune-Inspired Anomaly Detection

Nastaran Darabi, Devashri Naik, Sina Tayebati, Dinithi Jayasuriya, Amit Ranjan Trivedi

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: LLM multi-agent decision making · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a decentralized bio-autonomic control framework with immune-inspired anomaly detection to improve resilience of LLM multi-agent systems in Ambient Intelligence environments.

Problem

Reliability of autonomous LLM agents deployed at scale in Ambient Intelligence environments, where isolated adaptive control, anomaly detection, or trust modeling are fragmented and scenario-specific.

Approach

Unifies adaptive control, anomaly detection, and trust modeling into a decentralized bio-autonomic control architecture for multi-agent LLM systems, drawing inspiration from biological and immune systems.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the Bio-Autonomic framework on top of the LLM backbone instead of using AutoAgentsmulti-agent LLM system · HumanEvalscore (0-100): 81.23 -> 88.52 (GPT-4o)Improved
add the Bio-Autonomic framework instead of H-MASmulti-agent LLM system · CIARscore (0-100): 62.34 -> 72.89 (GPT-4o)Improved
add the Bio-Autonomic framework to the Collab-Overcooked agentGPT-4o · Collab-Overcooked Level 6SR (%): 4.00 -> 20.00Improved
add the Bio-Autonomic framework to a small modelLlama3.1-8B · Collab-Overcooked Level 1SR (%): 4.00 -> 72.00Improved
add Bio-Autonomic under AUTOTRANSFORM faultGPT-4o · Collab-Overcooked Level 1SR (%): 65.80 -> 95.00Improved
use Bio-Autonomic instead of MADDPG under 20% semantic faultsmulti-agent LLM system · AUTOINJECT 20%PDF (%): -65.0 -> -4.8Improved
use Bio-Autonomic instead of AutoAgents under 20% semantic faultsmulti-agent LLM system · AUTOINJECT 20%ERR (%): 12.5 -> 93.4Improved
add direct trust ledger (versus none) (ablation)Bio-Autonomic · AUTOTRANSFORM single malicious agentCFHR (%): 65.4 -> 15.2Improved
add gossip-based reputation dissemination to direct trust (ablation)Bio-Autonomic · AUTOTRANSFORM single malicious agentMAI: 0.73 -> 0.94Improved
add gossip-based reputation dissemination to direct trust (ablation)Bio-Autonomic · AUTOTRANSFORM single malicious agentERR (%): 74.0 -> 93.4Improved

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