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.
Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
MemSyco-Bench is a benchmark covering five tasks to evaluate memory-induced sycophancy in LLM agents, testing rejection of invalid memory, scope respect, conflict resolution, update tracking, and valid personalization.
A longitudinal qualitative study of 18 US users finds that LLMs deliver socioemotional support but also foster dependency, one-sided validation, and privacy risks because their designs prioritize engagement over well-being and lack care-based governance.
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.
-
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
MemSyco-Bench is a benchmark covering five tasks to evaluate memory-induced sycophancy in LLM agents, testing rejection of invalid memory, scope respect, conflict resolution, update tracking, and valid personalization.
-
Engagement-Optimized Care: When LLMs become Mental Health Infrastructure
A longitudinal qualitative study of 18 US users finds that LLMs deliver socioemotional support but also foster dependency, one-sided validation, and privacy risks because their designs prioritize engagement over well-being and lack care-based governance.