{"ID":2859696,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04488","arxiv_id":"2510.04488","title":"Multi-Agent Collaborative Intelligence: Dual-Dial Control for Reliable LLM Reasoning","abstract":"Multi-agent debate often wastes compute by using a fixed adversarial stance, aggregating without deliberation, or stopping on heuristics. We introduce MACI, an active controller with two independent dials that decouple information from behavior: an information dial that gates evidence by quality, and a behavior dial that schedules contentiousness from exploration to consolidation. A moderator tracks disagreement, overlap, evidence quality, and argument quality, and halts when gains plateau. We provide theory-lite guarantees for nonincreasing dispersion and provable termination, with a budget-feasible scheduler. Across clinical diagnosis and news-bias tasks, MACI improves accuracy and calibration while reducing tokens, and converts residual uncertainty into precision RAG plans that specify what to retrieve next. We use a cross-family LLM judge (CRIT) as a conservative soft weight and stop signal, validated for order invariance and judge-swap stability; stability depends on using high-capability judges. MACI turns debate into a budget-aware, measurable, and provably terminating controller.","short_abstract":"Multi-agent debate often wastes compute by using a fixed adversarial stance, aggregating without deliberation, or stopping on heuristics. We introduce MACI, an active controller with two independent dials that decouple information from behavior: an information dial that gates evidence by quality, and a behavior dial th...","url_abs":"https://arxiv.org/abs/2510.04488","url_pdf":"https://arxiv.org/pdf/2510.04488v1","authors":"[\"Edward Y. Chang\",\"Ethan Y. Chang\"]","published":"2025-10-06T04:52:17Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.IT\"]","methods":"[\"Large Language Model\",\"LoRA\"]","has_code":false}