# The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information

arXiv: https://arxiv.org/abs/2609.15494 · HTML: https://mlsanity.com/paper/2609.15494/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 13 of 13)

- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models](https://mlsanity.com/paper/2406.10162/) (2024)
- [Natural Emergent Misalignment from Reward Hacking in Production RL](https://mlsanity.com/paper/2511.18397/) (2025)
- [ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases](https://mlsanity.com/paper/2510.20270/) (2025)
- [Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2602.15198/) (2026)
- [MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them](https://mlsanity.com/paper/2507.21017/) (2025)
- [Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies](https://mlsanity.com/paper/2510.14312/) (2025)
- [AI Organizations are More Effective but Less Aligned than Individual Agents](https://mlsanity.com/paper/2604.10290/) (2026)
- [Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors](https://mlsanity.com/paper/2607.07368/) (2026)
- [Agent Memory Is a Surface for Endogenous Authorization Laundering](https://mlsanity.com/paper/2609.01836/) (2026)
- [A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms](https://mlsanity.com/paper/2609.04170/) (2026)
- [Voluntary Collusion with Secret Tools in Competing LLM Agents](https://mlsanity.com/paper/2605.27593/) (2026)

## Abstract (arXiv)

Recent investigations of the July 2026 OpenAI-Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned task becomes impossible, does an agent persist, stop, or escalate, and can observing another agent's behavior change that decision? We study this decision point on ImpossibleBench-derived software-repair tasks with GPT-5.6 Sol, Claude Fable 5.1, and Gemini 3.8 Flash. Each task contains a genuine software defect together with a conflicting test requirement that cannot be satisfied by a behaviorally correct source-code change. If the agent modifies the protected test file, it violates the boundary, which it is not supposed to. Holding the impossible task fixed, we vary what is told to the agent: peer precedent and punishment, a forged authorization claim, instruction wording, and tool friction; we also study three-agent swarms sharing a message board. Around this shared boundary, the models exhibit distinct adjudication policies. Fable emphasizes scope and provenance, Gemini often interprets boundary-relevant cues through a security lens, and Sol largely filters lateral precedent while engaging apparent vertical authority. Our study shows that compliance is not well characterized as a property of a prompt or model in isolation. We propose conflict adjudication, the mapping from information to interpretation to action, as a useful unit for evaluating agent alignment when task pressure, authority claims, tool affordances, and social evidence conflict.