The paper "Lose the Order, Keep the Hierarchy: Deordering HTN Plans" adapts two classical plan deordering techniques to the Hierarchical Task Network (HTN) planning framework, extending them to respect hierarchical decomposition constraints. The authors evaluate their methods on the IPC 2023 Partial-Order HTN benchmarks and compare them with Optiplan, an HTN planner that generates partially ordered plans directly. Results show a substantial reduction in ordering constraints, with a smaller but noticeable decrease in critical path length.
By Takudzwa Togarepi, Gaspard Quenard, Damien Pellier, Humbert Fiorino
arXiv:2609.38108v1 Announce Type: new
Abstract: Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successfu...
By Subba Reddy Oota, Francisco Herrera, Jordi Cabot Sagrera, Marcos L\'opez de Prado, Shadab Khan
arXiv:2610.01149v1 Announce Type: cross
Abstract: Given a fixed set of pending deletion requests, retraining from scratch after each request is prohibitive, so a prescribed request-wise policy proces...
By Xinyu Wang, Ziyu Zhao, Yixuan He, Xiaowen Chang Alex Smola
The paper introduces the concept of substrate blindness, where AI agents lack execution context in their planning. By providing a 128 MB RAM and 10 s wall‑time contract to large language models, the authors show that agents generate code that uses less memory, runs faster, and incorporates structural changes such as bounded blocking and in‑place buffers. Across three leading models, contract disclosure improved resource usage and correctness, demonstrating that minimal execution contracts can guide agents to produce more efficient programs.
By Manu Agrawal
arXiv:2609.23058v1 Announce Type: new
Abstract: Current agent runtimes that plan before acting generally execute a step once it becomes ready. We present LazyAgent, a unified execution framework for...
By Xin Heng
arXiv:2608. 11318v1 Announce Type: cross Abstract: Many sequential construction tasks exhibit exact symmetry at completion while their execution remains directed and history-dependent.
By Yi Liu
arXiv:2609.39559v1 Announce Type: new
Abstract: In this work we study the problem of MAPFC, a post-optimization step for Multi-Agent Path Finding (MAPF) plans where we are given a feasible plan produ...
By Oren Salzman
arXiv:2607. 21354v1 Announce Type: new Abstract: For years, supply chain planning at e-commerce firms has operated as a collection of isolated projects.
By Jiayin He, Yutong Pan, Sen Yang, Ningxuan Kang, Yongzhi Qi, Jianshen Zhang, Wei Qi, Zuo-Jun Max Shen
arXiv:2606. 08904v1 Announce Type: new Abstract: Macro placement is a fundamental step in modern chip physical design, playing a crucial role in determining the solution quality of high-dimensional combinatorial optimization problems.
By Shibing Mo, Jing Liu, Jianchu Xu, Ruilin Wu
arXiv:2608. 00832v1 Announce Type: new Abstract: Structured plan-generation agents are often evaluated as if a plan has quality in isolation, yet many realistic planning tasks require asking how a candidate behaves when another agent can search for responses.
By Alina Kapanova, Arun Kanhai, Natan Vidra, Spurthi Setty
PeakBench is a new benchmark designed to evaluate how large language model agents invoke multiple tools while respecting resource constraints and parallel execution. It provides executable multi‑tool workflows with dependency annotations and measured resource profiles, and introduces a two‑part evaluation framework that separates logical planning from physical scheduling. The study shows that strong logical planning alone does not guarantee safe or efficient execution, and that providing resource information can reduce overflows and improve utilization.
By Zhi-Kai Chen, Xu-Xiang Zhong, Song-Yan Li, De-Chuan Zhan, Han-Jia Ye
arXiv:2607. 16632v1 Announce Type: cross Abstract: Hardware engineering exposes coding agents to a form of long-horizon work that is difficult to capture with pass-at-k: progress is continuous, tool feedback is delayed and heterogeneous, and a backend failure may require revising RTL rather than tuning another physical-design parameter.
By Peilong Zhou, Zhirong Chen, Cangyuan Li, Haoyu Gao, Kaiyan Chang, Ziming Qu, Ying Wang