arXiv AI
When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
1d ago
Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems
The paper introduces Independent–Communicate–Revise (ICR), a framework that isolates communication effects in large language model multi‑agent systems by fixing initial reasoning and measuring how messages influence answer revision. ICR evaluates correction, preservation, and selectivity across four reasoning benchmarks, revealing that similar overall accuracy can mask divergent revision behaviors. The study shows that richer messages can both improve and harm outcomes, and that receiver policies can shift preservation and correction dynamics differently across tasks.
arXiv AI
Aug 17
Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
arXiv:2608. 14375v1 Announce Type: new Abstract: Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer.
arXiv AI
Jun 2
Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
arXiv:2606. 01637v1 Announce Type: cross Abstract: Large language models are increasingly used in multi-agent systems, where they see and respond to other agents' answers.
arXiv AI
Sep 1
Candidate supply and answer selection shape the value of LLM judging in multi-agent systems
arXiv:2608.25937v2 Announce Type: replace Abstract: Multi-agent systems (MAS) sometimes already have the potential to answer correctly, but still report a wrong answer. Explaining this outcome is dif...
Hugging Face Trending Papers
Jul 29
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
Latent communication in large language model (LLM)-based multi-agent systems (MAS) transmits continuous internal representations instead of text, but greater representational capacity does not establish that the receiver uses task-relevant information. End-task performance alone also cannot reveal whether an observed effect depends on message presence, content generated for the evaluated example, or information supplied by a separate agent.
arXiv AI
Jun 19
Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol
arXiv:2606. 19356v1 Announce Type: cross Abstract: When multi-agent LLM systems produce bad answers, not all failures are equal: some answers are grounded in the right material but incomplete, while others are simply ungrounded and should be stopped.