Memory Sharing for Large Language Model based Agents
This addresses the limitation of example diversity in LLM-based agents for open-ended tasks, though it appears incremental as an enhancement to existing in-context learning approaches.
The paper tackles the problem of LLM-based agents producing divergent outputs on open-ended questions due to limited example diversity, by introducing a Memory Sharing framework that enables real-time memory sharing among multiple agents to enhance in-context learning. Experimental results show the framework significantly improves agent performance on open-ended questions across three specialized domains.
The adaptation of Large Language Model (LLM)-based agents to execute tasks via natural language prompts represents a significant advancement, notably eliminating the need for explicit retraining or fine tuning, but are constrained by the comprehensiveness and diversity of the provided examples, leading to outputs that often diverge significantly from expected results, especially when it comes to the open-ended questions. This paper introduces the Memory Sharing, a framework which integrates the real-time memory filter, storage and retrieval to enhance the In-Context Learning process. This framework allows for the sharing of memories among multiple agents, whereby the interactions and shared memories between different agents effectively enhance the diversity of the memories. The collective self-enhancement through interactive learning among multiple agents facilitates the evolution from individual intelligence to collective intelligence. Besides, the dynamically growing memory pool is utilized not only to improve the quality of responses but also to train and enhance the retriever. We evaluated our framework across three distinct domains involving specialized tasks of agents. The experimental results demonstrate that the MS framework significantly improves the agents' performance in addressing open-ended questions.