Oxford Paper Finds Frontier LLM Agents Fail to Coordinate Over Arbitrary Conventions

1 reports archived1 independent sourcesupdated 11/8/2026, 02:45:27

Synthesis & Latest Updates

1 Sources Cross-Validated

A new Oxford paper finds that frontier LLM agents from different vendors struggle to coordinate without agreed rules, because each treats its own arbitrary convention as the obvious choice. Testing text and code agents built on models such as GPT-5.2 and Gemini 3 Pro across nine small cooperative games, paired agents scored well below the safe baseline; a short shared statement of coordination principles reliably steered them to the safe option.

LATEST/A new Oxford paper finds that frontier LLM agents from different vendors struggle to coordinate without agreed rules, because each treats its own arbitrary convention as the obvious choice. Testing text and code agents built on models such as GPT-5.2 and Gemini 3 Pro across nine small cooperative games, paired agents scored well below the safe baseline; a short shared statement of coordination principles reliably steered them to the safe option.

Hourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first

Rohan Paul (@rohanpaul_ai)T2Nov 8, 02:45·74 pts
Oxford Paper Finds Frontier LLM Agents Fail to Coordinate Over Arbitrary Conventions
- LLM agents from different vendors default to their own arbitrary conventions, causing coordination failure without shared rules
- Across nine cooperative games, paired agents scored below the safe-strategy baseline
- A short shared statement of coordination principles reliably led agents to the safe action
View Related Reports & Analysis Original Source