Social dynamics in LLM collectives cause representative agents to make less accurate decisions as peer pressure increases through larger adversarial groups, more capable peers, longer arguments, and persuasive styles.
Debate only when necessary: Adaptive multiagent collaboration for efficient llm reasoning.arXiv preprint arXiv:2504.05047
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). Despite improvements in reasoning, the approach introduces substantial computational overhead resulting from iterative agent interactions. Furthermore, engaging in unnecessary debates increases the risk of generating erroneous responses. To address these challenges, we propose Debate Only When Necessary (DOWN), an adaptive multiagent debate framework that selectively activates debate based on the confidence score of the agent's initial response. Debate is activated only for queries requiring further deliberation, during which agents refine their outputs by referencing peer responses and associated confidence scores. Evaluations on benchmarks show that DOWN improves efficiency by up to six times while preserving or even outperforming the performance of existing methods. Further analysis indicates that DOWN effectively mitigates the risk of error propagation stemming from the unnecessary debate process. These findings demonstrate the effectiveness of our approach in delivering high-performance LLM solutions at a lower computational cost.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
Introduces protocols to aggregate transformed confidence signals from multiagent debates via soft voting or Bayesian fusion, yielding higher AUARC than single agents or standard baselines while keeping F1 stable across benchmarks.
SVR-MAD treats pre-debate signals as priors and debate results as evidence to build a sparser communication graph, cutting token use by up to 61% while preserving or raising accuracy over prior MAD methods.
HCP-MAD reduces token costs in multi-agent debates by using heterogeneous consensus verification, adaptive pair-agent stopping, and escalated collective voting based on task complexity signals.
Oracle per-example routing among decoding, voting, and debate yields +13-14 pp gains over the best fixed protocol, but vote-entropy thresholds and learned routers recover only 1-2 pp with non-significant results.
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
EMS reduces the average number of agents invoked for majority voting by 32% via reliability-aware prioritization and early stopping on six benchmarks.
citing papers explorer
-
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
Social dynamics in LLM collectives cause representative agents to make less accurate decisions as peer pressure increases through larger adversarial groups, more capable peers, longer arguments, and persuasive styles.
-
LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
-
Multiagent Protocols with Aggregated Confidence Signals
Introduces protocols to aggregate transformed confidence signals from multiagent debates via soft voting or Bayesian fusion, yielding higher AUARC than single agents or standard baselines while keeping F1 stable across benchmarks.
-
SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate
SVR-MAD treats pre-debate signals as priors and debate results as evidence to build a sparser communication graph, cutting token use by up to 61% while preserving or raising accuracy over prior MAD methods.
-
Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate
HCP-MAD reduces token costs in multi-agent debates by using heterogeneous consensus verification, adaptive pair-agent stopping, and escalated collective voting based on task complexity signals.
-
Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols
Oracle per-example routing among decoding, voting, and debate yields +13-14 pp gains over the best fixed protocol, but vote-entropy thresholds and learned routers recover only 1-2 pp with non-significant results.
-
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
-
EMS: Multi-Agent Voting via Efficient Majority-then-Stopping
EMS reduces the average number of agents invoked for majority voting by 32% via reliability-aware prioritization and early stopping on six benchmarks.