Long-horizon language agents make interdependent decisions across multiple rounds, forming growing planning graphs in which later decisions depend on earlier states, observations, and tool outputs. Errors in these graphs can therefore propagate through subsequent decisions and amplify over long rollouts. Correcting the most visible failure may therefore fix a symptom while leaving the core that drives downstream errors unchanged. Replaying the entire planning graph provides the opposite extreme, but becomes increasingly expensive as the graph grows and forces an LLM to reason over substantial irrelevant context. We study planning-graph repair: given a failed rollout, the goal is to identify and correct the compact core responsible for continued error propagation while preserving the remainder of the graph. We first evaluate a range of practical engineering repair strategies, including single-error and TopK repair, temporal windows, neighborhood expansion, cascade-aware repair, and full-graph LLM correction. We then propose ReCore (Repair the Core), which models the coupled propagation of node and edge errors to identify the core of a failed planning graph. Rather than repairing the largest observed errors or expanding a fixed local neighborhood, ReCore selects a connected core whose correction maximally reduces residual error amplification, and exposes only this core to the LLM for diagnosis and repair. We also theoretically establish a bound on long-horizon planning regret. Extensive experiments on synthetic Agent Calling-Tree graphs and the Who\&When attribution benchmark show that ReCore improves long-horizon stabilization and root-cause localization by targeting high-amplification repair regions, matching full-context recovery with up to $7.4\times$ fewer tokens for every successful repair.
AnchorSIPS: A Synthetic Dataset and Evaluation Resource for Evidence-Supported Psychosis-Risk Symptom Measurement
Monash University(莫纳什大学);Orygen(奥瑞金);The University of Melbourne(墨尔本大学);Swinburne University of Technology(斯威本科技大学);University of Liverpool(利物浦大学);Khalifa University(哈利法大学)
Repairing LLM-Generated Specifications with Deterministic Diagnosis
University of Oxford(牛津大学);University of Illinois Chicago(伊利诺伊大学芝加哥分校);Politecnico di Milano(米兰理工大学);The Pennsylvania State University(宾夕法尼亚州立大学);Institute for Decentralized AI (IDAI)(去中心化人工智能研究所(IDAI))
NEXUS: Learning Safety Constraints and Action Models for Safe and Robust Embodied Planning
School of Artificial Intelligence and Automation(人工智能与自动化学院);Huazhong University of Science and Technology(华中科技大学);School of Software(软件学院);Henan University(河南大学);Institute of Information Engineering(信息工程研究所);Chinese Academy of Sciences(中国科学院);School of Cyberspace Security(网络空间安全学院);University of the Chinese Academy of Sciences(中国科学院大学);Peking University(北京大学)
Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
East China Normal University(华东师范大学);Nanyang Technological University(南洋理工大学);Singapore Management University(新加坡管理大学);Xi’an University of Architecture and Technology(西安建筑科技大学)
A Probabilistic Neural Twin for Treatment Planning in Peripheral Pulmonary Artery Stenosis
University of Notre Dame(圣母大学);Stanford University(斯坦福大学);University of Pittsburgh School of Medicine(匹兹堡大学医学院);UPMC Children’s Hospital of Pittsburgh(匹兹堡UPMC儿童医院)
VISTA: Knowledge-Driven Vessel Trajectory Imputation with Repair Provenance
Department of Computer Science, Aalborg University, Denmark(计算机科学系,奥胡斯大学,丹麦);School of Computer Science and Engineering, Northeastern University, Shenyang, China(计算机科学与工程学院,东北大学,沈阳,中国)
Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraints
Spatial AI & Robotics (SAIR) Lab, University at Buffalo, NY 14260(空间人工智能与机器人实验室,布法罗大学,纽约州,14260);Robotics Institute, Carnegie Mellon University, PA 15213(机器人研究所,卡内基梅隆大学,宾夕法尼亚州,15213)
Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention
State Key Lab of Processors, Institute of Computing Technology, CAS(中国科学院计算技术研究所处理器重点实验室);School of Advanced Interdisciplinary Sciences, CAS(中国科学院高等交叉学科学院);University of Chinese Academy of Sciences(中国科学院大学);Institute of Microelectronics, CAS(中国科学院微电子研究所)