Preference Estimation via Opponent Modeling in Multi-Agent Negotiation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911601243717632 |
|---|---|
| author | Konishi, Yuta Yamamoto, Kento Sonomoto, Eisuke Takeda, Rikuho Furukawa, Ryo Muraki, Yusuke Shimizu, Takafumi Fukumura, Kazuma Kanemoto, Yuya Ito, Takayuki Ding, Shiyao |
| author_facet | Konishi, Yuta Yamamoto, Kento Sonomoto, Eisuke Takeda, Rikuho Furukawa, Ryo Muraki, Yusuke Shimizu, Takafumi Fukumura, Kazuma Kanemoto, Yuya Ito, Takayuki Ding, Shiyao |
| contents | Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural language interactions, resulting in unstable and incomplete preference estimation. Although Large Language Models (LLMs) enable rich semantic understanding of utterances, it remains challenging to quantitatively incorporate such information into a consistent opponent modeling. To tackle this issue, we propose a novel preference estimation method integrating natural language information into a structured Bayesian opponent modeling framework. Our approach leverages LLMs to extract qualitative cues from utterances and converts them into probabilistic formats for dynamic belief tracking. Experimental results on a multi-party benchmark demonstrate that our framework improves the full agreement rate and preference estimation accuracy by integrating probabilistic reasoning with natural language understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15687 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Preference Estimation via Opponent Modeling in Multi-Agent Negotiation Konishi, Yuta Yamamoto, Kento Sonomoto, Eisuke Takeda, Rikuho Furukawa, Ryo Muraki, Yusuke Shimizu, Takafumi Fukumura, Kazuma Kanemoto, Yuya Ito, Takayuki Ding, Shiyao Computation and Language Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural language interactions, resulting in unstable and incomplete preference estimation. Although Large Language Models (LLMs) enable rich semantic understanding of utterances, it remains challenging to quantitatively incorporate such information into a consistent opponent modeling. To tackle this issue, we propose a novel preference estimation method integrating natural language information into a structured Bayesian opponent modeling framework. Our approach leverages LLMs to extract qualitative cues from utterances and converts them into probabilistic formats for dynamic belief tracking. Experimental results on a multi-party benchmark demonstrate that our framework improves the full agreement rate and preference estimation accuracy by integrating probabilistic reasoning with natural language understanding. |
| title | Preference Estimation via Opponent Modeling in Multi-Agent Negotiation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.15687 |