Hugging Face Trending Papers

When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Coupling Diagnostic for Machine Collectives

Read the original on Hugging Face Trending Papers →

Collective intelligence research treats disagreement as evidence of epistemic diversity: if agents express different views, the group should retain capacity to revise. In LLM collectives this proxy can break: agents can produce diverse-looking arguments while preserving the same conclusion.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
1d ago

MELD: A Protocol for Merging Knowledge Across Distributed Agentic Memories

arXiv:2608. 16357v1 Announce Type: cross Abstract: Autonomous agents share a transport and can call each other's tools, but they cannot share what they know: no protocol lets two agents' memories reconcile a fact phrased two ways, link related facts held apart, or reconcile contradictory knowledge without silently discarding either claim.

By Lauri Lov\'en, Jaakko Sauvola, Jukka Riekki, Sasu Tarkoma