Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measurement protocol that caches five independently generated messages and replays the same downstream solver, called the integrator, with each message available or hidden. The replay comparison measures a m
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “Wrong but Useful: Trajectory Value Beyond Answer Correctness” ≈ “AgentCore-8B””
- PossiblePossibly related (embedding) · 49%AgentTrace →
- FuzzySimilar title/name (fuzzy) · 87%SWE-agent/SWE-agent →
“Fuzzy title match (0.94): “Wrong but Useful: Trajectory Value Beyond Answer Correctness” ≈ “SWE-agent/SWE-agent””
- FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “Wrong but Useful: Trajectory Value Beyond Answer Correctness” ≈ “zhayujie/CowAgent””
- FuzzySimilar title/name (fuzzy) · 66%open-multi-agent/open-multi-agent →
“Fuzzy title match (0.78): “Wrong but Useful: Trajectory Value Beyond Answer Correctness” ≈ “open-multi-agent/open-multi-agent””
- FuzzySimilar title/name (fuzzy) · 59%NousResearch/hermes-agent →
“Fuzzy title match (0.73): “Wrong but Useful: Trajectory Value Beyond Answer Correctness” ≈ “NousResearch/hermes-agent””
- FuzzySimilar title/name (fuzzy) · 59%bojieli/ai-agent-book →
“Fuzzy title match (0.73): “Wrong but Useful: Trajectory Value Beyond Answer Correctness” ≈ “bojieli/ai-agent-book””
- LinkedLinked via arxiv author · 85%Chih-Hsuan Yang →
“Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages”