Pith. sign in

REVIEW 4 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.04784 v1 pith:5H6C6QMM submitted 2024-06-07 cs.CL cs.AI

Ruihan Yang , Jiangjie Chen , Yikai Zhang , Siyu Yuan , Aili Chen , Kyle Richardson , Yanghua Xiao , Deqing Yang This is my paper · ORCID
classification cs.CLcs.AI
keywords agentshigh-levellanguageselfgoalenvironmentsfeedbackgoalsachieve
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic

    cs.AI 2024-12 conditional novelty 5.0 of 10

    Across three planning domains, LLMs perform better as comparative rankers of intermediate plans than as direct solvers or verifiers, and one-shot heuristic guidance improves ranking.

  2. Who Speaks Next? Multi-party AI Discussion Leveraging the Systematics of Turn-taking in Murder Mystery Games

    cs.CL 2024-12 conditional novelty 5.0 of 10

    Letting the current speaker select the next speaker through adjacency pair rules makes AI agents' group conversations in a murder mystery game more coherent and cooperative.

  3. Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches

    cs.AI 2025-01 conditional novelty 3.0 of 10

    This survey argues that embodiment, symbol grounding, causality, and memory are the foundational principles needed to make large language models achieve artificial general intelligence.

  4. A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios

    cs.CL 2024-12 conditional novelty 3.0 of 10

    LLM-based game-playing agents are surveyed across choice-focused and communication-focused games, with a comparative performance table and future directions.

Pith tools