error cascade mitigation 1language model alignment 1multi-agent dialogue 1peer ranking 1sycophancy 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems
Vira Kasprova, Amruta Parulekar, Abdulrahman AlRabah +5
The paper investigates how informing language model agents about each other's tendency to agree with users (sycophancy) can reduce error cascades in multi‑agent discussions and boo…
cs.AI2026
AgentAbstain: Do LLM Agents Know When Not to Act?
Xun Liu, Yi Evie Zhang, Vira Kasprova +5
Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents…