Pith. sign in

REVIEW 5 cited by

DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models

Not yet reviewed by Pith; the record is open.

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 2404.03275 v3 pith:HJMBG2GM submitted 2024-04-04 cs.RO cs.AI

classification cs.ROcs.AI
keywords planningtaskdeltallmslanguagelargemodelsefficient
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advancements in Large Language Models (LLMs) have sparked a revolution across many research fields. In robotics, the integration of common-sense knowledge from LLMs into task and motion planning has drastically advanced the field by unlocking unprecedented levels of context awareness. Despite their vast collection of knowledge, large language models may generate infeasible plans due to hallucinations or missing domain information. To address these challenges and improve plan feasibility and computational efficiency, we introduce DELTA, a novel LLM-informed task planning approach. By using scene graphs as environment representations within LLMs, DELTA achieves rapid generation of precise planning problem descriptions. To enhance planning performance, DELTA decomposes long-term task goals with LLMs into an autoregressive sequence of sub-goals, enabling automated task planners to efficiently solve complex problems. In our extensive evaluation, we show that DELTA enables an efficient and fully automatic task planning pipeline, achieving higher planning success rates and significantly shorter planning times compared to the state of the art. Project webpage: https://delta-llm.github.io/

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

    cs.RO 2026-08 conditional novelty 6.0 of 10

    A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.

  2. Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object Search

    cs.RO 2026-03 accept novelty 6.0 of 10

    SCOUT matches LLM planners on open-world interactive object search by scoring 3D scene-graph nodes with lightweight models distilled from LLM relational priors, at far lower compute cost.

  3. Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning

    cs.AI 2025-06 conditional novelty 6.0 of 10

    TAPAS uses several specialized language-model agents to generate, correct, and adapt symbolic planning problems, reporting high benchmark accuracy and a virtual-home execution demo.

  4. Triple-S: A Collaborative Multi-LLM Framework for Solving Long-Horizon Implicative Tasks in Robotics

    cs.RO 2025-08 conditional novelty 5.0 of 10

    Triple-S combines instruction simplification, retrieval of similar examples, and a summary-based library update to improve LLM-generated robot policy code on long-horizon implicative tasks.

  5. Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions

    cs.RO 2025-06 conditional novelty 5.0 of 10

    Using robot actions and LLM visual reasoning, the system identifies deformability properties of unseen objects with up to 78.57% accuracy, which helps plan bin-packing at over 96% success after replanning.

Pith tools