SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals

2024/06/07 by Ruihan Yang, Jiangjie Chen, Yang, Ruihan +13 · 9 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Intelligent Tutoring Systems and Adaptive Learning #Multi-Agent Systems and Negotiation #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2406.04784

openalex publication_date 2024/06/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Language agents powered by large language models (LLMs) are increasingly valuable as decision-making tools in domains such as gaming and programming. However, these agents often face challenges in achieving high-level goals without detailed instructions and in adapting to environments where feedback is delayed. In this paper, we present SelfGoal, a novel automatic approach designed to enhance agents' capabilities to achieve high-level goals with limited human prior and environmental feedback. The core concept of SelfGoal involves adaptively breaking down a high-level goal into a tree structure of more practical subgoals during the interaction with environments while identifying the most useful subgoals and progressively updating this structure. Experimental results demonstrate that SelfGoal significantly enhances the performance of language agents across various tasks, including competitive, cooperative, and deferred feedback environments. Project page: https://selfgoal-agent.github.io.

Cited by

• TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review
• Intelligent Design 4.0: Paradigm Evolution Toward the Agentic AI Era
• Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs
• ARIA: Training Language Agents with Intention-Driven Reward Aggregation
• Cost-Awareness in Tree-Search LLM Planning: A Systematic Study
• From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
• Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction
• Evaluating the Goal-Directedness of Large Language Models
• GraphicBench: A Planning Benchmark for Graphic Design with Language Agents

Related

• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
• SELF: Self-Evolution with Language Feedback
• A Survey on Complex Tasks for Goal-Directed Interactive Agents
• Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning
• Sub-goal Distillation: A Method to Improve Small Language Agents