cs.MANov 17, 2026

Surfacing Disagreement Beats Resolving It: A Gated Ablation Study of Provenance-Weighted Memory for Multi-Agent Debate

Authors: Ziaullah Khan, Abdul Rehman Khalid, Shrestha Nischal Lal, Nheng Vanchhay, Md Ariful Islam Mozumder, Hee-Cheol Kim

Organizations: Department of Digital Anti-Aging Healthcare, Inje University, Gimhae, Republic of Korea · Department of Computer Engineering, Inje University, Gimhae, Republic of Korea

Abstract

Shared memory for multi-agent debate is usually built to resolve inconsistency: retrieval returns one winning fact and the disagreement disappears before any agent sees it. We ask whether that is correct. In DebateGraph, four backends share one contract (read/write/snapshot), so five mechanisms from the agent-memory literature can be removed independently under a fixed budget, each gated on a pre-declared threshold. Across 39 runs one survives: preserving contradictions and passing the ranked conflict set to the debate, rather than collapsing it to a winner, improves F1 by +0.340 (95% CI [+0.267, +0.414]) and cuts attack success from 22 to 7 of 122 poisoned items (McNemar exact p=0.0003), at equal cost. Reaching it meant fixing a bottleneck in our harness: conflict sets are built only over retrieved edges, and our pre-declared cap left three quarters of planted contradictions unretrievable, first measuring the mechanism at +0.084. The effect replicates on two retrieval substrates and directionally on HotpotQA documents. No other mechanism survives, and two are worse than inert: once contradictions reach the prompt, a write trust-gate and the router's provenance features each cost accuracy (-0.075 and -0.096 F1). The gate fails structurally: poisoned objects are always entities the graph already contains, against 53% of gold, so groundedness scores the lie above a truthful first mention. We release the harness, attack set, and logs, and argue that silently reconciling memory is the assumption worth abandoning.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. HEDGE: Gated Hypergraph Memory for Scalable Multi-Agent Debate

    Oct 28, 2026Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zirui ZhouMemory Management for LLM AgentsMulti-Agent Debate

  2. EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium

    May 10, 2026Yuqiao Meng, Luoxi Tang, Sakshi Sunil Narvekar +4Multi-Agent DebateAgent Memory Poisoning

  3. Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory

    Apr 4, 2026Albert Sadowski, Jarosław A. ChudziakAgent MemoryMulti-Agent Reasoning