Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry

• URL: http://arxiv.org/abs/2607.01661v1
• Date: Thu, 02 Jul 2026 03:41:25 GMT
• Title: Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry
• Abstract summary: We show that when all agents are given identical evidence, deliberation collapses into herding rather than genuine belief revision.<n>We propose a framework combining relevance-aware evidence routing, rationale-based iterative deliberation, and confidence-weighted aggregation.<n>On PolyGym, a benchmark of 375 binary forecasting questions, InfoDelphi outperforms the strongest single-agent and multi-agent baselines.
• Score: 1.8983854039418835
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent systems are increasingly used for forecasting future events, as deliberation among multiple LLMs is believed to improve reasoning and calibration. Yet existing approaches overlook a critical design choice: what information each agent receives. When all agents are given identical evidence, deliberation collapses into herding rather than genuine belief revision, leaving multi-agent systems little better than a single agent. We identify this as a fundamental gap and propose designed information asymmetry to close it: by partitioning evidence into shared public and disjoint private subsets, each agent holds exclusive knowledge that can only reach others through deliberation. We theoretically show that this decomposition reduces inter-agent error correlation, and instantiate it in InfoDelphi, a framework combining relevance-aware evidence routing, rationale-based iterative deliberation, and confidence-weighted aggregation. On PolyGym, a benchmark of 375 binary forecasting questions derived from real-world prediction markets, InfoDelphi outperforms the strongest single-agent and multi-agent baselines by 12--18% in Brier score and 4--8 percentage points in accuracy. More detailed experiments confirm that removing information asymmetry eliminates most deliberation gains, establishing diversity of input as the key enabler of effective multi-agent reasoning.

Related papers

• EMS: Multi-Agent Voting via Efficient Majority-then-Stopping [62.95000188335248]
  We propose an Efficient Majority-then-Stopping (EMS) to improve reasoning efficiency.<n>EMS prioritizes agents based on task-aware reliability and terminates the reasoning pipeline the moment a majority is achieved.<n>EMS consistently reduces the average number of invoked agents by 32%.
  arXiv  Detail & Related papers  (2026-04-03T08:29:50Z)
• Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty [15.933557806106071]
  We propose Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty (A2MAML)<n>A2MAML is a principled approach for uncertainty-aware, modality-level collaboration.<n>Experiments on connected autonomous driving scenarios for collaborative accident detection demonstrate that A2MAML consistently outperforms both single-agent and collaborative baselines.
  arXiv  Detail & Related papers  (2026-02-04T17:01:31Z)
• PAMAS: Self-Adaptive Multi-Agent System with Perspective Aggregation for Misinformation Detection [29.17300778511738]
  Misinformation on social media poses a critical threat to information credibility.<n>Large language model-empowered multi-agent systems (MAS) present a promising paradigm to combat this threat.<n>We propose PAMAS, a framework with perspective aggregation to highlight anomaly cues and alleviate information drowning.
  arXiv  Detail & Related papers  (2026-02-03T06:18:39Z)
• Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning [112.16686518063456]
  We introduce textbfMulti-Agent Test-Time Reinforcement Learning (MATTRL), a framework that injects structured textual experience into multi-agent deliberation at inference time.<n>MATTRL forms a multi-expert team of specialists for multi-turn discussions, retrieves and integrates test-time experiences, and reaches consensus for final decision-making.<n>Across challenging benchmarks in medicine, math, and education, MATTRL improves accuracy by an average of 3.67% over a multi-agent baseline, and by 8.67% over comparable single-agent baselines
  arXiv  Detail & Related papers  (2026-01-14T17:57:43Z)
• Internalizing Self-Consistency in Language Models: Multi-Agent Consensus Alignment [22.305033366660187]
  Language Models (LMs) are inconsistent reasoners, often generating contradictory responses to identical prompts.<n>We formalize self-consistency as an intrinsic property of well-aligned reasoning models and introduce Multi-Agent Consensus Alignment (MACA)<n>MACA enables agents to teach themselves to be more decisive and concise, and better leverage peer insights in multi-agent settings without external supervision.
  arXiv  Detail & Related papers  (2025-09-18T17:27:28Z)
• MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection [84.75972919995398]
  This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles.<n>The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent, and (iv) a web-scraped data analyzer.<n>Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches.
  arXiv  Detail & Related papers  (2025-08-13T19:14:48Z)
• GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning [9.24980723036746]
  GAM-Agent is a game-theoretic multi-agent framework for enhancing vision-language reasoning.<n>It formulates the reasoning process as a non-zero-sum game between base agents--each specializing in visual perception subtasks--and a critical agent that verifies logic consistency and factual correctness.<n>Our approach is modular, scalable, and generalizable, offering a path toward reliable and explainable multi-agent multimodal reasoning.
  arXiv  Detail & Related papers  (2025-05-29T12:37:34Z)
• HiddenBench: Assessing Collective Reasoning in Multi-Agent LLMs via Hidden Profile Tasks [12.203366267017737]
  We introduce HiddenBench, the first benchmark for evaluating collective reasoning in multi-agent LLMs.<n>To ground the benchmark, we formalize the paradigm with custom tasks and show that GPT-4.1 groups fail to integrate distributed knowledge.<n>We then construct the full benchmark, spanning 65 tasks drawn from custom designs, prior human studies, and automatic generation.
  arXiv  Detail & Related papers  (2025-05-15T19:22:54Z)
• ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs [61.07130026622437]
  Large Language Models (LLMs) still struggle with natural language reasoning tasks. Motivated by the society of minds, we propose ReConcile. A multi-model multi-agent framework designed as a round table conference among diverse LLM agents.
  arXiv  Detail & Related papers  (2023-09-22T17:12:45Z)
• On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring [105.13668993076801]
  A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees. We study this question in a general framework for interactive decision making with multiple agents. We show that characterizing the statistical complexity for multi-agent decision making is equivalent to characterizing the statistical complexity of single-agent decision making.
  arXiv  Detail & Related papers  (2023-05-01T06:46:22Z)
• Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecasting [61.02295959343446]
  This work first proposes a novel concept, collaborative uncertainty (CU), which models the uncertainty resulting from interaction modules.<n>We build a general CU-aware regression framework with an original permutation-equivariant uncertainty estimator to do both tasks of regression and uncertainty estimation.<n>We apply the proposed framework to current SOTA multi-agent trajectory forecasting systems as a plugin module.
  arXiv  Detail & Related papers  (2022-07-11T21:17:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.