Pith. sign in

REVIEW 5 cited by

Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification

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 2405.15414 v1 pith:G76C73UB submitted 2024-05-24 cs.AI

classification cs.AI
keywords creativeagentstasksverificationbuildinglubanautonomousembodied
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Building open agents has always been the ultimate goal in AI research, and creative agents are the more enticing. Existing LLM agents excel at long-horizon tasks with well-defined goals (e.g., `mine diamonds' in Minecraft). However, they encounter difficulties on creative tasks with open goals and abstract criteria due to the inability to bridge the gap between them, thus lacking feedback for self-improvement in solving the task. In this work, we introduce autonomous embodied verification techniques for agents to fill the gap, laying the groundwork for creative tasks. Specifically, we propose the Luban agent target creative building tasks in Minecraft, which equips with two-level autonomous embodied verification inspired by human design practices: (1) visual verification of 3D structural speculates, which comes from agent synthesized CAD modeling programs; (2) pragmatic verification of the creation by generating and verifying environment-relevant functionality programs based on the abstract criteria. Extensive multi-dimensional human studies and Elo ratings show that the Luban completes diverse creative building tasks in our proposed benchmark and outperforms other baselines ($33\%$ to $100\%$) in both visualization and pragmatism. Additional demos on the real-world robotic arm show the creation potential of the Luban in the physical world.

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.

  1. The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

    cs.AI 2025-09 accept novelty 6.0 of 10

    Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.

  2. CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks

    cs.AI 2025-08 conditional novelty 6.0 of 10

    A causality-inspired LLM planning framework with task graphs, counterfactual rule checks, and busy-rate path assignment improves multi-agent Minecraft task completion in reported experiments.

  3. Rethinking Agentic Reinforcement Learning In Large Language Models

    cs.AI 2026-04 unverdicted novelty 3.0 of 10

    The paper reviews conceptual foundations, methodological innovations, effective designs, critical challenges, and future directions for LLM-based Agentic Reinforcement Learning.

  4. Rethinking Agentic Reinforcement Learning In Large Language Models

    cs.AI 2026-04 unverdicted novelty 2.0 of 10

    This review synthesizes conceptual foundations, methods, challenges, and future directions for agentic reinforcement learning in large language models.

  5. Rethinking Agentic Reinforcement Learning In Large Language Models

    cs.AI 2026-04 unverdicted novelty 2.0 of 10

    The paper surveys the conceptual foundations, methodological innovations, challenges, and future directions of agentic reinforcement learning frameworks that embed cognitive capabilities like meta-reasoning and self-r...

Pith tools