代理性知識自我意識

摘要

大型語言模型（LLMs）在各種代理規劃任務中已展現出顯著的性能。然而，傳統的代理規劃方法採用了一種「大水漫灌」的策略，不加區分地將黃金軌跡、外部反饋和領域知識注入代理模型中。這種做法忽視了人類在決策過程中情境自我意識的基本認知原則——即動態評估情境需求並在決策過程中策略性地運用資源的能力。為填補這一空白，我們提出了具備知識自我意識的代理，這是一種新穎的範式，使基於LLM的代理能夠自主調節知識的利用。具體而言，我們提出了KnowSelf，這是一種以數據為中心的方法，它賦予代理像人類一樣的知識自我意識。具體來說，我們設計了一種啟發式情境判斷標準，用於在代理自我探索的軌跡上標記特殊符號，以收集訓練數據。通過兩階段的訓練過程，代理模型能夠通過生成特定的特殊符號在不同情境間切換，以最小成本實現最佳規劃效果。我們的實驗表明，KnowSelf在不同任務和模型上均能超越多種強基線，且僅需極少的外部知識。代碼可在https://github.com/zjunlp/KnowSelf獲取。

English

Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks. However, traditional agent planning approaches adopt a "flood irrigation" methodology that indiscriminately injects gold trajectories, external feedback, and domain knowledge into agent models. This practice overlooks the fundamental human cognitive principle of situational self-awareness during decision-making-the ability to dynamically assess situational demands and strategically employ resources during decision-making. We propose agentic knowledgeable self-awareness to address this gap, a novel paradigm enabling LLM-based agents to autonomously regulate knowledge utilization. Specifically, we propose KnowSelf, a data-centric approach that applies agents with knowledgeable self-awareness like humans. Concretely, we devise a heuristic situation judgement criterion to mark special tokens on the agent's self-explored trajectories for collecting training data. Through a two-stage training process, the agent model can switch between different situations by generating specific special tokens, achieving optimal planning effects with minimal costs. Our experiments demonstrate that KnowSelf can outperform various strong baselines on different tasks and models with minimal use of external knowledge. Code is available at https://github.com/zjunlp/KnowSelf.

代理性知識自我意識

Agentic Knowledgeable Self-awareness

摘要

Summary

Support

Support