REVIEW 10 cited by
Improving Multi-Agent Debate with Sparse Communication Topology
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Multi-agent debate has proven effective in improving large language models quality for reasoning and factuality tasks. While various role-playing strategies in multi-agent debates have been explored, in terms of the communication among agents, existing approaches adopt a brute force algorithm -- each agent can communicate with all other agents. In this paper, we systematically investigate the effect of communication connectivity in multi-agent systems. Our experiments on GPT and Mistral models reveal that multi-agent debates leveraging sparse communication topology can achieve comparable or superior performance while significantly reducing computational costs. Furthermore, we extend the multi-agent debate framework to multimodal reasoning and alignment labeling tasks, showcasing its broad applicability and effectiveness. Our findings underscore the importance of communication connectivity on enhancing the efficiency and effectiveness of the "society of minds" approach.
Forward citations
Cited by 10 Pith papers
-
ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
A perturbation-based framework measures how value opinions propagate through multi-agent LLM systems, revealing that susceptibility varies by value, model, and topology.
-
DHEvo: Data-Algorithm Based Heuristic Evolution for Generalizable MILP Solving
DHEvo co-evolves MILP training instances and diving heuristics, improving generalization over existing LLM-based heuristic generation methods.
-
MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering
MUPA combines three ordering-based reasoning paths with a reflection agent that verifies and fuses answer-evidence pairs, reaching 30.3% and 47.4% grounded QA accuracy on NExT-GQA and DeVE-QA with a 7B model.
-
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Sharing rollouts between decentralized language models during RL post-training improved cumulative rewards by up to 94% over an isolated baseline in the paper's best configuration.
-
How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs
A leader LLM trained with a GRPO variant that conditions on frozen agent responses improves both collaborative and zero-shot accuracy on BBH, MATH, and MMLU.
-
AgentDNS: A Root Domain Naming System for LLM Agents
AgentDNS is a proposed system that gives LLM agents a DNS-like namespace and discovery service for finding and invoking third-party tools and agents across vendors.
-
S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency
S2-MAD's decision mechanism filters redundant viewpoints and conditionally skips participation, cutting token costs by up to 94.5% versus standard multi-agent debate while keeping accuracy within about 2 points in the...
-
Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates
The paper proposes GVIC, a multi-agent debate method using graduated vigilance and interval communication, and reports improved harmlessness and helpfulness over single-agent and classical debate baselines.
-
Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives
A survey proposes a macro-meso-micro value framework for agentic AI alignment and maps applications, methods, and benchmarks onto it.
-
Multi-LLM Text Summarization
Using multiple LLMs to generate and select summaries raises ROUGE and BLEU scores on ArXiv and GovReport compared with single-LLM chunk-and-concatenate baselines.
Discussion (0). Continue with ORCID to comment.