Strategic Communication and Language Bias in Multi-Agent LLM Coordination
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912687211937792 |
|---|---|
| author | Buscemi, Alessio Proverbio, Daniele Di Stefano, Alessandro Han, The Anh Castignani, German Liò, Pietro |
| author_facet | Buscemi, Alessio Proverbio, Daniele Di Stefano, Alessandro Han, The Anh Castignani, German Liò, Pietro |
| contents | Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Research shows that the way strategic scenarios are framed linguistically can affect cooperation. This paper explores whether allowing agents to communicate amplifies these language-driven effects. Leveraging FAIRGAME, we simulate one-shot and repeated games across different languages and models, both with and without communication. Our experiments, conducted with two advanced LLMs-GPT-4o and Llama 4 Maverick-reveal that communication significantly influences agent behavior, though its impact varies by language, personality, and game structure. These findings underscore the dual role of communication in fostering coordination and reinforcing biases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00032 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Strategic Communication and Language Bias in Multi-Agent LLM Coordination Buscemi, Alessio Proverbio, Daniele Di Stefano, Alessandro Han, The Anh Castignani, German Liò, Pietro Multiagent Systems Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Research shows that the way strategic scenarios are framed linguistically can affect cooperation. This paper explores whether allowing agents to communicate amplifies these language-driven effects. Leveraging FAIRGAME, we simulate one-shot and repeated games across different languages and models, both with and without communication. Our experiments, conducted with two advanced LLMs-GPT-4o and Llama 4 Maverick-reveal that communication significantly influences agent behavior, though its impact varies by language, personality, and game structure. These findings underscore the dual role of communication in fostering coordination and reinforcing biases. |
| title | Strategic Communication and Language Bias in Multi-Agent LLM Coordination |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2508.00032 |