one-agent-s-context-carries-planted-misinformation-wrong-answer CLM-0313When one agent's context carries planted misinformation, the wrong answer persists through multi-agent debate and other agents often adopt it, yet debate still degrades less than a single misinformed agent (relevant misinformation cut single-agent accuracy by 16-25% on CWQ), especially when most agents are unexposed; consensus protocols were more stable than voting under peer pressure, and a misinformed majority can steer the group.
Capability: Getting more from several models than from one
Observed on
Reasoning, knowledge and alignment tasks with intent-based misinformation injected into one or more agents' context, open models such as GLM-4, 2026; debate with voting versus cons.
Sources
- Injected rather than naturally occurring misinformation; group composition and protocol effects are the useful design guidance.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- In multi-agent LLM networks where a correct minority peer disagrees with an agreeing majority, ranking peers by raw divergence from the receiver's own belief systematically prefers the wrong peers, while scoring each peer by asserted precision divided by its divergence from a second-order model of what that peer should have concluded given its data subscription isolates the correct one.Getting more from several models than from one · reviewed by AI
- In fully connected networks of LLM agents (Llama 3.2-8B, 50 agents, 10 rounds) where a fixed minority holds an unchanging extreme stance, neutral agents' textual justifications converge on the biased agents' vocabulary faster and more completely than their numeric stances do, so monitoring only the text overstates how much the group actually agrees.Getting more from several models than from one · reviewed by AI
- In multi-agent debate with 3 open-weight agents over 3 rounds, giving each agent a memory of past debates helps only if retrieval is conditioned on the current consensus ratio and peer responses are annotated with memory-derived reliability labels; randomly inserting past cases is the weakest retrieval policy and plain task-similarity retrieval trails every consensus-conditioned variant.Getting more from several models than from one · reviewed by AI
- In LLM multi-agent systems that reflect after failure, restricting reflection to the single agent responsible for the first incorrect step — located by a trained step-level correctness scorer and paired with a counterfactually generated corrected step — raises task success more than having every agent reflect on the trajectory, because reflections written by agents that behaved correctly enter their memory as misleading guidance for later tasks.Getting more from several models than from one · reviewed by AI
- On knowledge, math and medical QA benchmarks with 8B open backbones (Llama-3.1-8B-Instruct, Qwen3-8B), the accuracy advantage of multi-agent debate pipelines over a single agent can be matched by a single-turn single agent whose hidden state is steered by a query-composed mixture of role vectors, at roughly a twentieth of the token cost, so the benefit of these pipelines comes from multi-perspective specialization rather than from inter-agent text exchange.Getting more from several models than from one · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: Debate configurations where a single misinformed agent reliably flips a correct majority, or where consensus is less robust than voting.