Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation
This addresses reasoning challenges in LLMs for complex tasks, though it appears incremental as an enhancement to existing agent-style approaches.
The authors tackled the limitations of chain-of-thought prompting (hallucination, interpretability, controllability) by developing AgentCOT, an LLM-based autonomous agent framework that solves complex problems through multi-round generation with action selection and evidence collection. Their method achieved substantial improvements over competitive approaches on six benchmarks.
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.