Positive Experience Reflection for Agents in Interactive Text Environments
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912104678686720 |
|---|---|
| author | Lippmann, Philip Spaan, Matthijs T. J. Yang, Jie |
| author_facet | Lippmann, Philip Spaan, Matthijs T. J. Yang, Jie |
| contents | Intelligent agents designed for interactive environments face significant challenges in text-based games, a domain that demands complex reasoning and adaptability. While agents based on large language models (LLMs) using self-reflection have shown promise, they struggle when initially successful and exhibit reduced effectiveness when using smaller LLMs. We introduce Sweet&Sour, a novel approach that addresses these limitations in existing reflection methods by incorporating positive experiences and managed memory to enrich the context available to the agent at decision time. Our comprehensive analysis spans both closed- and open-source LLMs and demonstrates the effectiveness of Sweet&Sour in improving agent performance, particularly in scenarios where previous approaches fall short. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_02223 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Positive Experience Reflection for Agents in Interactive Text Environments Lippmann, Philip Spaan, Matthijs T. J. Yang, Jie Computation and Language Artificial Intelligence Machine Learning Intelligent agents designed for interactive environments face significant challenges in text-based games, a domain that demands complex reasoning and adaptability. While agents based on large language models (LLMs) using self-reflection have shown promise, they struggle when initially successful and exhibit reduced effectiveness when using smaller LLMs. We introduce Sweet&Sour, a novel approach that addresses these limitations in existing reflection methods by incorporating positive experiences and managed memory to enrich the context available to the agent at decision time. Our comprehensive analysis spans both closed- and open-source LLMs and demonstrates the effectiveness of Sweet&Sour in improving agent performance, particularly in scenarios where previous approaches fall short. |
| title | Positive Experience Reflection for Agents in Interactive Text Environments |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2411.02223 |