# Paper: Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game

---
type: paper
title: Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game
authors: Subhendu Bhandary, Federico Carucci, Christos Charalambous, Francesca Dilisante, Ksenia Dvorkina, Anna Garbo, Jiaqi Liang, Riccardo Vasellini, et al.
year: 2026
venue: arXiv
url: https://arxiv.org/abs/2606.28456
code_url:
source: arxiv
collected_at: 2026-07-08
published_at: 2026-06-26
updated_at: 2026-06-26
status: queued
relevance: high
topics:
  - agent-safety
  - memory
  - multi-agent
methods:
  -
benchmarks:
  -
models:
  -
datasets:
  - cs.MA
  - cs.AI
related_concepts:
  -
related_jobs:
  -
related_experiments:
  -
related_projects:
  -
collection_score: 18
collection_queries: ai-agent, llm-agent, multi-agent-llm
---

## One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

## Why Collected

- matched queries: ai-agent, llm-agent, multi-agent-llm
- inferred topics: agent-safety, memory, multi-agent
- arXiv categories: cs.MA, cs.AI
- collection score: 18

## Review Checklist

- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
- Does it include a benchmark, dataset, code, or reproducible experimental setup?
- Should it be promoted from `queued` to `skimmed` or `summarized`?

## Links

- arXiv: https://arxiv.org/abs/2606.28456