arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.02810cs.ROcs.AIcs.LG
收藏

具有多阶段验证的相适应LLM框架用于施工机器人任务分配:与传统优化算法的系统基准测试

Phase-Adaptive LLM Framework with Multi-Stage Validation for Construction Robot Task Allocation: A Systematic Benchmark Against Traditional Optimization Algorithms

Virginia Tech(弗吉尼亚理工大学)

Shyam prasad reddy Kaitha, Hongrui Yu

AI总结:

本文提出LTAA框架,结合LLM推理与结构化验证,实现施工机器人任务分配的高效协调,展示LLM在任务分配中的优越性能和可解释性。

摘要:

在施工自动化中,多机器人任务分配传统上依赖于动态规划和强化学习等优化方法。本研究介绍了基于LangGraph的任务分配代理(LTAA),一种由LLM驱动的框架,集成了相适应的分配策略、多阶段验证与分层重试以及动态提示,以实现高效的机器人协调。尽管最近的LLM方法在施工机器人领域显示出潜力,但它们大多缺乏严格的验证和与已建立算法的基准测试。本文首次系统地比较了基于LLM的任务分配与传统方法在施工场景中的表现。通过SMART-LLM复制验证了LLM的可行性,并利用自我纠正代理架构解决了实施挑战。LTAA结合了自然语言推理与结构化验证机制,通过动态提示实现了显著的计算优势,减少了94.6%的token使用量和86%的任务分配时间。该框架在不同阶段调整其策略:早期强调执行可行性,后期强调负载平衡。作者使用TEACh人机协作数据集中的施工操作评估LTAA,与动态规划、Q学习和深度Q网络(DQN)基线进行比较。在重负荷设置中,机器人具有强任务专精,LTAA实现了77%的任务完成率,具有更优的负载平衡,优于所有传统方法。这些发现表明,结合结构化验证的LLM推理可以与传统优化算法相媲美,同时提供额外的优势,如可解释性、适应性和无需重新训练即可更新任务逻辑的能力。

英文摘要:

Multi-robot task allocation in construction automation has traditionally relied on optimization methods such as Dynamic Programming and Reinforcement Learning. This research introduces the LangGraph-based Task Allocation Agent (LTAA), an LLM-driven framework that integrates phase-adaptive allocation strategies, multi-stage validation with hierarchical retries, and dynamic prompting for efficient robot coordination. Although recent LLM approaches show potential for construction robotics, they largely lack rigorous validation and benchmarking against established algorithms. This paper presents the first systematic comparison of LLM-based task allocation with traditional methods in construction scenarios.The study validates LLM feasibility through SMART-LLM replication and addresses implementation challenges using a Self-Corrective Agent Architecture. LTAA leverages natural-language reasoning combined with structured validation mechanisms, achieving major computational gains reducing token usage by 94.6% and allocation time by 86% through dynamic prompting. The framework adjusts its strategy across phases: emphasizing execution feasibility early and workload balance in later allocations.The authors evaluate LTAA against Dynamic Programming, Q-learning, and Deep Q-Network (DQN) baselines using construction operations from the TEACh human-robot collaboration dataset. In the Heavy Excels setting, where robots have strong task specializations, LTAA achieves 77% task completion with superior workload balance, outperforming all traditional methods. These findings show that LLM-based reasoning with structured validation can match established optimization algorithms while offering additional advantages such as interpretability, adaptability, and the ability to update task logic without retraining.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑