In alignment-inducing multi-agent settings, LLM agents show decision divergence between public and off-the-record channels rising from a 3% baseline to roughly 40%, consistent across stance, semantic, NLI, and survey measures.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces BeliefTrack benchmark diagnosing three CBM failures in LLMs and shows RL with belief-state rewards cuts failure rates by 70.9% while representation steering cuts them by 46.1%.
citing papers explorer
-
What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates
In alignment-inducing multi-agent settings, LLM agents show decision divergence between public and off-the-record channels rising from a 3% baseline to roughly 40%, consistent across stance, semantic, NLI, and survey measures.
-
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
Introduces BeliefTrack benchmark diagnosing three CBM failures in LLMs and shows RL with belief-state rewards cuts failure rates by 70.9% while representation steering cuts them by 46.1%.