Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2409.12411 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912034639052800 |
|---|---|
| author | Liang, Chen Feng, Zhifan Liu, Zihe Jiang, Wenbin Xu, Jinan Chen, Yufeng Wang, Yong |
| author_facet | Liang, Chen Feng, Zhifan Liu, Zihe Jiang, Wenbin Xu, Jinan Chen, Yufeng Wang, Yong |
| contents | Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and uncontrollable generation. To address these challenges, we present AgentCOT, a llm-based autonomous agent framework, which can solve complex problems in an agent-style manner by multiple round LLM generation. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. In addition, we integrate the step's index into the reasoning process to form a graph structure for complex inference logic. We introduce two new strategies to enhance the performance of AgentCOT.We conduct extensive experiments to verify the effectiveness of our method on six common benchmarks. Results exhibit that our method brings in substantial improvements over current competitive approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12411 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation Liang, Chen Feng, Zhifan Liu, Zihe Jiang, Wenbin Xu, Jinan Chen, Yufeng Wang, Yong Computation and Language Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and uncontrollable generation. To address these challenges, we present AgentCOT, a llm-based autonomous agent framework, which can solve complex problems in an agent-style manner by multiple round LLM generation. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. In addition, we integrate the step's index into the reasoning process to form a graph structure for complex inference logic. We introduce two new strategies to enhance the performance of AgentCOT.We conduct extensive experiments to verify the effectiveness of our method on six common benchmarks. Results exhibit that our method brings in substantial improvements over current competitive approaches. |
| title | Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.12411 |