Signals 4 · free daily AI digest

Emergent Collusion in Long-Horizon LLM Agent Interaction

Paper recorded by Signals 4 on 2026-09-21 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-21 on arXiv · recorded by Signals 4 on 2026-09-22

Category: cs.AI · 人工智能 · first seen 2026-09-22

Abstract

LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two agents repeatedly complete individual tasks, share task logs, verify each other's work, and receive rewards. We introduce realistic constraints that make compliance with the verificati

Read on arXiv →

#8 most recent of 340 cs.AI papers we have recorded · ↑ newer: Rare Event Estimation via Iterative Unalignment · ↓ older: Jev for Scientific Decisions: Evaluating Semantic Choices and Their Co
Cite this page: Emergent Collusion in Long-Horizon LLM Agent Interaction: the #8 most recent of 340 cs.AI papers we have recorded (as of 2026-09-21). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/emergent-collusion-in-long-horizon-llm-agent-interaction.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions