Transferable Expertise for Autonomous Agents via Real-World Case-Based Learning

arXiv cs.AI / 4/15/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses a limitation of LLM-based autonomous agents in real-world scenarios: they often fail to reliably leverage task structure, constraints, and prior experience.
It proposes a case-based learning framework that turns experience from past tasks into reusable knowledge assets (including task-relevant knowledge, analytical prompts, and operational skills).
The authors evaluate the approach on a unified benchmark covering six complex task categories and compare it against Zero-Shot, Few-Shot, Checklist Prompt, and Rule Memory baselines.
Results indicate the method delivers consistently strong performance across all task types, with the largest benefits on the most complex tasks.
The analysis suggests the advantage grows as task complexity increases and that knowledge gained by one agent can be transferred and reused by other agents, supporting the goal of “professional” real-world agents.

Abstract

LLM-based autonomous agents perform well on general reasoning tasks but still struggle to reliably use task structure, key constraints, and prior experience in complex real-world settings. We propose a case-based learning framework that converts experience from past tasks into reusable knowledge assets, allowing agents to transfer prior case experience to new tasks and perform more structured analysis. Unlike methods based mainly on pretrained knowledge or static prompts, our framework emphasizes extracting and reusing task-relevant knowledge, analytical prompts, and operational skills from real cases. We evaluate the method on a unified benchmark of six complex task categories and compare it with Zero-Shot, Few-Shot, Checklist Prompt, and Rule Memory baselines. Results show that our method achieves consistently strong performance across all tasks and matches or outperforms the best baseline in every case, with especially clear gains on more complex tasks. Further analysis shows that the advantage of case-based learning increases with task complexity, and that practical knowledge acquired by one agent can be reused by others. These findings suggest that case-based learning offers a promising path for building professional agents for real-world work.