{"ID":5675106,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-05T03:36:18.476506982Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01661","arxiv_id":"2607.01661","title":"Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry","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.","short_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 colla...","url_abs":"https://arxiv.org/abs/2607.01661","url_pdf":"https://arxiv.org/pdf/2607.01661v1","authors":"[\"Yuante Li\",\"Yicheng Tao\",\"Kate Zhang\",\"Taozhi Wang\",\"Gefei Gu\",\"Yaxin Zhou\"]","published":"2026-07-02T03:41:25Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}