SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction

• URL: http://arxiv.org/abs/2608.01652v1
• Date: Mon, 03 Aug 2026 03:43:57 GMT
• Title: SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction
• Abstract summary: SyncPlan is a plan-execute-correct framework for long-horizon coordination in dynamic environments.<n>During execution, explicit wait primitives and deadlock detection enforce inter-agent and agent-environment dependencies.<n>A lightweight Plan Staleness Detector continuously assesses the remaining plan and triggers replanning when environmental changes invalidate its assumptions.
• Score: 30.543497829249972
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based multi-agent coordination faces a fundamental trade-off between efficiency and adaptivity in dynamic environments. Existing approaches typically rely on repeated LLM invocations or multi-round communication to adapt decisions during execution, introducing substantial latency and making coordination vulnerable to asynchronous progress and environmental changes. Conversely, one-shot planning reduces coordination overhead but produces open-loop plans that can quickly become stale or fail when actions depend on other agents and the environment. We introduce SyncPlan, a plan-execute-correct framework for long-horizon coordination through explicit synchronization and adaptive correction. Given the state and team-level task, a centralized LLM coordinator generates per-agent action chains in a single planning call. During execution, explicit wait primitives and deadlock detection enforce inter-agent and agent-environment dependencies, while a lightweight Plan Staleness Detector continuously assesses the remaining plan and triggers replanning when environmental changes invalidate its assumptions. We further optimize the coordinator through SFT and planning-oriented RL with dense task progress and outcome-level execution feedback. Experiments on the public Overcooked benchmark and the complex Honor of Kings environment show that SyncPlan achieves state-of-the-art task success rates while using less than 0.05% of the wall-clock runtime compared with existing LLM-based coordinators. Code and datasets will be made publicly available.

Related papers

• Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks [48.90302419915548]
  Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in smart factories, warehouses, and service robotics.<n>We propose LDT-Coord, a networked coordination framework built upon a lightweight digital twin (DT)<n>Specifically, each agent independently selects its intended action and reports both the action decision and a structured temporal constraint over shared resources to the DT server.
  arXiv  Detail & Related papers  (2026-07-10T12:10:31Z)
• TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL [72.7712729541565]
  Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context.<n>A single global prompt does not specify which sub-event should be realized in each chunk, while naively switching to step-wise prompts often leads to delayed reactions, blended step semantics, and error propagation across prompt transitions.<n>We address these challenges with TempAct, a planner--executor reinforcement learning framework that jointly optimize temporal decomposition and step-conditioned execution for temporally plausible AR video generation.
  arXiv  Detail & Related papers  (2026-06-26T12:19:28Z)
• Melding LLM and temporal logic for reliable human-swarm collaboration in complex scenarios [17.56189537207367]
  We introduce a neuro-symbolic framework for long-horizon human-swarm collaboration.<n>We formalize mission goals and operational rules as temporal logic formulas and admissible task orderings as task automata.<n>An event-triggered interaction protocol limits operator involvement to sparse, high-level confirmation and guidance.
  arXiv  Detail & Related papers  (2026-05-08T15:32:14Z)
• Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs [52.26652574704317]
  Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes.<n>We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems.
  arXiv  Detail & Related papers  (2026-05-07T14:19:17Z)
• UMBRELLA: Uncertainty-aware Multi-robot Reactive Coordination under Dynamic Temporal Logic Tasks [5.794342083222513]
  This paper addresses the problem of coordinating multi-robot systems for collaborative tasks involving dynamic and moving targets.<n>We explicitly model the uncertainty in target motion prediction via Conformal Prediction (CP)<n>The proposed framework (UMBRELLA) combines the Monte Carlo Tree Search (MCTS) over partial plans with uncertainty-aware rollouts.
  arXiv  Detail & Related papers  (2026-03-26T12:40:04Z)
• DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration [18.250351934101463]
  DR. WELL is a decentralized neurosymbolic framework for cooperative multi-agent planning.<n>Agents propose candidate roles and commit to a joint allocation under consensus and environment constraints.<n>Each agent independently generates and executes a symbolic plan for its role without revealing detailed trajectories.
  arXiv  Detail & Related papers  (2025-11-06T18:37:18Z)
• ParaCook: On Time-Efficient Planning for Multi-Agent Systems [62.471032881396496]
  Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks.<n>We present ParaCook, a benchmark for time-efficient collaborative planning.
  arXiv  Detail & Related papers  (2025-10-13T16:47:07Z)
• Benchmarking LLMs' Swarm intelligence [51.648605206159125]
  Large Language Models (LLMs) show potential for complex reasoning, yet their capacity for emergent coordination in Multi-Agent Systems (MAS) remains largely unexplored.<n>We introduce SwarmBench, a novel benchmark designed to systematically evaluate tasks of LLMs acting as decentralized agents.<n>We propose metrics for coordination effectiveness and analyze emergent group dynamics.
  arXiv  Detail & Related papers  (2025-05-07T12:32:01Z)
• Robotouille: An Asynchronous Planning Benchmark for LLM Agents [7.574421886354134]
  Asynchronous planning is essential for agents that must account for time delays, reason over diverse long-horizon tasks, and collaborate with other agents.<n>We introduce Robotouille, a benchmark environment designed to test agents' ability to handle long-horizon asynchronous scenarios.<n>Our results show that ReAct (gpt4-o) achieves 47% on synchronous tasks but only 11% on asynchronous tasks, highlighting significant room for improvement.
  arXiv  Detail & Related papers  (2025-02-06T05:50:37Z)
• Bottom-up mechanism and improved contract net protocol for the dynamic task planning of heterogeneous Earth observation resources [61.75759893720484]
  Earth observation resources are becoming increasingly indispensable in disaster relief, damage assessment and related domains. Many unpredicted factors, such as the change of observation task requirements, to the occurring of bad weather and resource failures, may cause the scheduled observation scheme to become infeasible. A bottom-up distributed coordinated framework together with an improved contract net are proposed to facilitate the dynamic task replanning for heterogeneous Earth observation resources.
  arXiv  Detail & Related papers  (2020-07-13T03:51:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.