We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| willis-richard/evollm | canonical | 1 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| strip_code_markers | Ran | willis-richard/evollm/src/evollm/create_strategies.py code served (permissive licence) · get_code("4dca0486cbd06b40") |
| test_algorithm | Not yet run | willis-richard/evollm/src/evollm/create_strategies.py code served (permissive licence) · get_code("5e81a27934cc79f7") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
As autonomous agents become more prevalent, understanding their collective behaviour in strategic interactions is crucial. This study investigates the emergent cooperative tendencies of systems of Large Language Model (LLM) agents in a social dilemma. Unlike previous research where LLMs output individual actions, we prompt state-of-the-art LLMs to generate complete strategies for iterated Prisoner's Dilemma. Using evolutionary game theory, we simulate populations of agents with different strategic dispositions (aggressive, cooperative, or neutral) and observe their evolutionary dynamics. Our findings reveal that different LLMs exhibit distinct biases affecting the relative success of aggressive versus cooperative strategies. This research provides insights into the potential long-term behaviour of systems of deployed LLM-based autonomous agents and highlights the importance of carefully considering the strategic environments in which they operate.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.16173")
get_code_for_paper("2501.16173")
have("2501.16173")
Connect an agent — have() is free.