Models delayed verification in multi-agent LLMs as graph consensus, derives stability thresholds (inverse golden ratio for delay two) via grounded Laplacian, and gives a supermodular greedy rule for corrector placement; experiments on five models confirm dose-delay oscillations.
Multi-agent consensus seeking via large language models
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
SIV-Bench is a new video benchmark with 2,792 clips and 5,455 QA pairs that evaluates MLLMs on social scene understanding, state reasoning, and dynamics prediction using social relation theory.
Reasoning modes make multi-agent LLM negotiation look more diverse without raising agreement rates; self-written short notes restore agreement while ready-made notes do not.
Systematic study of inter-agent communication in LLM multi-agent systems shows reasoning and verification are critical for performance, with a new augmentation technique recovering 86.2% of failures.
LLM facilitation in group charity allocation leaves consensus and participation equity unchanged while shifting specific allocations up to 5.5 points and increasing perceived trust.
A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.
Global Workspace Agents (GWA) is proposed as an active, event-driven cognitive architecture for LLMs featuring an entropy-based intrinsic drive and dual-layer memory to enable sustained self-directed agency.
Temperature and persona variations shape consensus speed in LLM multi-agent coding but produce no robust accuracy gains over single agents on human-annotated tutoring transcripts.
HEART coordinates role-specialized LLM agents to decompose instructions, validate reachability and constraints, and synthesize executable robotic plans, showing higher success than single-LLM baselines on household tasks.
The survey organizes LLM-based multi-agent collaboration mechanisms into a framework with dimensions of actors, types, structures, strategies, and coordination protocols, reviews applications across domains, and identifies challenges for future research.
The paper surveys LLM-based multi-agent systems, covering simulated domains, agent profiling and communication, mechanisms for capacity growth, and common benchmarks.
citing papers explorer
-
Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement
Models delayed verification in multi-agent LLMs as graph consensus, derives stability thresholds (inverse golden ratio for delay two) via grounded Laplacian, and gives a supermodular greedy rule for corrector placement; experiments on five models confirm dose-delay oscillations.
-
SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning
SIV-Bench is a new video benchmark with 2,792 clips and 5,455 QA pairs that evaluates MLLMs on social scene understanding, state reasoning, and dynamics prediction using social relation theory.
-
Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation
Reasoning modes make multi-agent LLM negotiation look more diverse without raising agreement rates; self-written short notes restore agreement while ready-made notes do not.
-
What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems
Systematic study of inter-agent communication in LLM multi-agent systems shows reasoning and verification are critical for performance, with a new augmentation technique recovering 86.2% of failures.
-
Real-Time Group Dynamics with LLM Facilitation: Evidence from a Charity Allocation Task
LLM facilitation in group charity allocation leaves consensus and participation equity unchanged while shifting specific allocations up to 5.5 points and increasing perceived trust.
-
Insider Attacks in Multi-Agent LLM Consensus Systems
A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.
-
"Theater of Mind" for LLMs: A Cognitive Architecture Based on Global Workspace Theory
Global Workspace Agents (GWA) is proposed as an active, event-driven cognitive architecture for LLMs featuring an entropy-based intrinsic drive and dual-layer memory to enable sustained self-directed agency.
-
Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding
Temperature and persona variations shape consensus speed in LLM multi-agent coding but produce no robust accuracy gains over single agents on human-annotated tutoring transcripts.
-
HEART: Coordination of Heterogeneous Expert Agents for Physically Grounded Robotic Task Planning
HEART coordinates role-specialized LLM agents to decompose instructions, validate reachability and constraints, and synthesize executable robotic plans, showing higher success than single-LLM baselines on household tasks.
-
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
The survey organizes LLM-based multi-agent collaboration mechanisms into a framework with dimensions of actors, types, structures, strategies, and coordination protocols, reviews applications across domains, and identifies challenges for future research.
-
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
The paper surveys LLM-based multi-agent systems, covering simulated domains, agent profiling and communication, mechanisms for capacity growth, and common benchmarks.