Skip to content

MediHive: A Decentralized Agent Collective for Medical Reasoning

🕒 Published (v1): 2026-03-28 05:57 UTC · Source: Arxiv · link

Ask a follow-up

Open an assistant pre-loaded with this paper's context.

💬 Ask ChatGPT✦ Ask Claude

TL;DR

MediHive is a decentralized multi-agent framework for medical question answering that replaces a central coordinator with a shared append-only memory pool and peer-to-peer agent interactions. Agents autonomously self-assign roles, debate conflicting evidence, and iteratively fuse peer outputs until convergence. On MedQA and PubMedQA, it outperforms centralized multi-agent baselines using only protocol design—no fine-tuning, retrieval, or external knowledge bases.

Problem

Centralized LLM multi-agent systems for medical reasoning suffer from three structural defects: (1) the coordinator agent is a scalability bottleneck under high query volume; (2) it is a single point of failure; (3) when one LLM instance simulates multiple roles, role leakage and knowledge disarray degrade output quality. Decentralized designs exist for general tasks (AgentNet, Symphony) but remain largely unadapted to high-stakes healthcare QA where accuracy, ethical reasoning, and uncertainty handling are critical.

Method

MediHive deploys \(N\) LLM agents (Llama-3.1-70B-Instruct in experiments) communicating solely through a passive, append-only shared memory pool \(M\). The pipeline has five phases:

  1. Self-Evolving Role Assignment: Each agent \(A_i\) proposes an initial role \(R_{i,0}\), posts it to \(M\), then reads all peers' proposals and refines to a final role \(R_i\) optimizing three criteria: Clarity, Differentiation, and Alignment to query \(Q\).

  2. Initial Analysis: Each agent independently produces \(({\rm Reasoning}_{i,1}, {\rm Ans}_{i,1}, c_{i,1})\)—a CoT trace, an answer, and a self-assessed confidence \(c_{i,1} \in [0,1]\)—posted to \(M\).

  3. Disagreement Detection and Conditional Debate: Every agent independently tallies peer votes. If agreement falls below threshold \(\tau_{\rm agree}\) (e.g., 0.8), a debate of \(T_{\rm debate}\) rounds activates. Each agent posts one of three argument types per round—Rebuttal, Defense, or Proposal—without yet updating its formal answer. The debate enriches the evidence base adversarially.

  4. Iterative Shared Fusion: Starting at round \(k=2\), agents read the full history (initial analyses + debate) and update \(({\rm Reasoning}_{i,k}, {\rm Ans}_{i,k}, c_{i,k})\). For \(k>2\), only the immediately prior round's peer outputs are re-read. The loop terminates when agreement exceeds \(\tau_{\rm agree}\) for two consecutive rounds or round limit \(K\) is reached.

  5. Reporter Aggregation: A post-hoc Reporter—not involved in reasoning—either confirms the supermajority answer or applies a confidence-weighted vote: $\(a^* = \arg\max_{a \in V} \sum_{i=1}^{N} c_{i,k} \cdot \mathbf{1}(a_{i,k} = a)\)$

Key Contributions

  • Decentralized MAS architecture for medical QA: no central coordinator; all role assignment, disagreement detection, and fusion are performed autonomously by peer agents via a shared memory pool.
  • Self-evolving role assignment with peer-aware refinement, ensuring diverse and query-relevant specialization without external assignment logic.
  • Conditional debate phase that activates only on detected disagreement, followed by an integrative iterative fusion stage that separates adversarial evidence-gathering from formal answer convergence.
  • Demonstrates that protocol design alone (without specialized training, RAG, or external tools) is sufficient to outperform centralized baselines on medical QA benchmarks.

Results

All baselines re-implemented with Llama-3.1-70B-Instruct for fair comparison.

  • MediHive — MedQA: 84.3% accuracy / 82.5 F1; PubMedQA: 78.4% / 76.8 F1; Avg: 81.4%
  • Centralized multi-agent system — 77.8% / 75.3%; Avg: 76.6%
  • MedAgents — 83.7% / 76.8%; Avg: 80.3%
  • Multiagent Debate — 80.4% / 78.2%; Avg: 79.3%
  • Best single-agent (Few-shot CoT+SC) — 74.4% / 73.8%; Avg: 74.1%
  • MediHive outperforms all single-agent and multi-agent baselines on average accuracy; achieves highest MedQA accuracy across all methods.

Limitations

  • All experiments use a single backbone (Llama-3.1-70B-Instruct); generalization across model families or smaller models is untested.
  • No external retrieval, knowledge graphs, or RAG—the system is entirely dependent on LLM parametric knowledge, which may be outdated or incomplete for niche biomedical topics.
  • Self-assessed confidence scores \(c_{i,k}\) are LLM-generated heuristics, not calibrated probabilities; the weighted vote aggregation inherits this calibration weakness.
  • \(\tau_{\rm agree}\), \(T_{\rm debate}\), \(K\), and \(N\) are fixed hyperparameters; the paper does not provide ablations over their sensitivity or cost-accuracy trade-offs.
  • Evaluation is closed-book on static QA benchmarks; real clinical deployment (streaming patient data, time constraints, regulatory requirements) is not addressed.
  • Fault-tolerance claims (agent failure resilience) are architectural arguments only—no empirical failure injection experiments are reported.

Relevance to Harnesses / Meta-Harnesses

MediHive is a concrete instantiation of a coordination harness: a structured runtime that orchestrates multiple LLM agents through a defined sequence of phases (role assignment → analysis → debate → fusion → aggregation) without delegating control-flow decisions to any single agent. The shared append-only memory pool functions as a harness substrate—analogous to a message bus or blackboard—that decouples agent communication from agent logic. The conditional debate gate (activate-on-disagreement) is a harness-level branching mechanism, and the Reporter's post-hoc aggregation is a harness-level synthesis step that mirrors how meta-harnesses consolidate sub-agent outputs. For researchers building harnesses, MediHive's separation of adversarial evidence enrichment (debate) from formal convergence (fusion) is a reusable protocol pattern.