{"slug": "consilience-conformally-calibrated-communication-control-for-hidden-profile", "title": "Consilience: Conformally Calibrated Communication Control for Hidden-Profile Multi-Agent Reasoning", "summary": "Researchers propose Consilience, an inference-time orchestration framework that steers and certifies multi-agent LLM communication under distributed private information, providing a distribution-free, finite-sample guarantee that one-step regret is bounded with probability at least 1 - alpha. On HiddenBench-style tasks across 12 language models, Consilience improves decision accuracy and communication efficiency over fixed and unstructured protocols, sometimes surpassing a full-information baseline.", "body_md": "arXiv:2608.20564v1 Announce Type: new\nAbstract: Multi-agent LLM systems can improve reasoning by pooling diverse perspectives, but their effectiveness depends on coordinating communication, particularly in hidden-profile settings where each agent holds only part of the evidence required for a correct decision. Existing protocols, including fixed schedules, round-robin exchange, and unstructured debate, provide no guarantee that a conversational action is appropriate. We propose Consilience, an inference-time orchestration framework that both steers and certifies multi-agent communication under distributed private information. At each turn, Consilience summarizes the discussion using a compact state capturing uncertainty, disagreement, evidence gain, redundancy, and premature consensus, then selects both a communication intervention (challenge, clarify, seek evidence, or route) and an appropriate speaker. Its central contribution is a round-wise conformal calibration procedure that provides a distribution-free, finite-sample guarantee: at each discussion round, conditional on reaching that round, the one-step regret of a controller's proposed action is bounded by a calibrated threshold with marginal probability at least 1 - alpha; an acceptance mechanism enforces the same guarantee for the executed action by replacing inadmissible proposals. On HiddenBench-style hidden-profile tasks spanning 12 open and closed weight language models, Consilience improves decision accuracy and communication efficiency over fixed and unstructured discussion protocols, sometimes surpassing a full-information baseline where every agent observes all evidence. These results demonstrate that certified adaptive communication control can be more valuable than increasing information availability, providing a practical mechanism for reliable multi-agent LLM coordination.", "url": "https://wpnews.pro/news/consilience-conformally-calibrated-communication-control-for-hidden-profile", "canonical_source": "https://arxiv.org/abs/2608.20564", "published_at": "2026-08-24 04:00:00+00:00", "updated_at": "2026-08-24 04:13:47.104829+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["Consilience", "HiddenBench", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/consilience-conformally-calibrated-communication-control-for-hidden-profile", "markdown": "https://wpnews.pro/news/consilience-conformally-calibrated-communication-control-for-hidden-profile.md", "text": "https://wpnews.pro/news/consilience-conformally-calibrated-communication-control-for-hidden-profile.txt", "jsonld": "https://wpnews.pro/news/consilience-conformally-calibrated-communication-control-for-hidden-profile.jsonld"}}