StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure

• URL: http://arxiv.org/abs/2607.11388v1
• Date: Mon, 13 Jul 2026 10:48:25 GMT
• Title: StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
• Abstract summary: StructAgent is a state-centered framework for maintaining compact, verifiable task progress.<n>It enables explicit progress checkpointing, evidence-driven task completion, targeted failure recovery, and tool-supported execution.<n>It generalizes beyond desktop environments to Minecraft, demonstrating the generality of our design.
• Score: 29.25570731801935
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use. However, real-world tasks are often long-horizon and involve evolving contexts containing accumulated observations, intermediate edits, failed attempts, and partially completed executions. Existing agents typically operate over raw interaction history, making task progress difficult to interpret, verify, and recover, which ultimately limits reliable long-horizon execution. In this paper, we argue that addressing this challenge requires explicitly structuring both the agent's state and workflow around a unified causal representation of task progress. We present \textbf{StructAgent}, a state-centered framework that introduces a unified state for maintaining compact, verifiable task progress and a structured workflow that regulates progress through verifier-backed state transitions. Building on this design, StructAgent further enables explicit progress checkpointing, evidence-driven task completion, targeted failure recovery, and tool-supported execution, while ensuring that all progress updates remain grounded in verification. Extensive experiments demonstrate that StructAgent consistently improves a wide range of LLM and VLM backbones on long-horizon computer-use tasks. On OSWorld-Verified, it improves Qwen3.5-9B from 27.0\% to 46.9\% success rate and Qwen3.5-27B from 31.6\% to 62.2\%, while achieving a new open-source state of the art of 78.9\% with MiniMax-M3. Moreover, the same framework generalizes beyond desktop environments to Minecraft, demonstrating the generality of our design.

Related papers

• Compiling and Benchmarking Task-State Horizons for Embodied Agents [2.8397380902242966]
  Frontier agentic models are increasingly deployed as high-level planners for long-horizon embodied tasks.<n>We define the span of task-relevant state transitions that an agent must track as task-state horizon (TSH)<n>We introduce RoboGraph, a robotic task compiler that translates state-transition dependencies into executable symbolic graphs.
  arXiv  Detail & Related papers  (2026-08-08T09:45:01Z)
• DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations [106.74348504930124]
  We introduce DocOps, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy.<n>Based on DocOps, we systematically evaluate representative closed- and open-source models across various agentic harnesses.<n>Our work exposes the capability boundaries of agents in maintaining global document consistency, shedding light on the future design of robust, non-destructive agents.
  arXiv  Detail & Related papers  (2026-07-22T07:52:59Z)
• A Task-State Representation for Long-Horizon Mobile GUI Agents [53.359524744953575]
  Task-State Representation (TSR) is a training-free framework that explicitly decouples task state from sensory input.<n> Experiments across four mobile GUI benchmarks validate TSR's effectiveness, yielding up to a 12 absolute point increase in success rate.
  arXiv  Detail & Related papers  (2026-07-01T06:37:21Z)
• GTA: Generating Long-Horizon Tasks for Web Agents at Scale [82.43869456830664]
  We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control.<n>We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage.<n>Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.
  arXiv  Detail & Related papers  (2026-05-28T01:05:50Z)
• Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems [36.485119937780524]
  We present Meta-Agent, a two-phase framework that automatically constructs and executes specialized multi-agent systems.<n>We introduce a three-level error attribution mechanism that distinguishes local, upstream, and structural failures.<n>Experiments against strong multi-agent baselines and ablation studies demonstrate consistent improvements in task success rate, error recovery, and workflow stability.
  arXiv  Detail & Related papers  (2026-05-24T19:38:54Z)
• Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows [67.92316850084575]
  We introduce Claw-Eval-Live, a live benchmark for workflow agents.<n>Each release is constructed from public workflow-demand signals.<n>Claw-Eval-Live records execution traces, audit logs, service state, and post-run workspace artifacts.
  arXiv  Detail & Related papers  (2026-04-30T17:23:19Z)
• ANCHOR: Branch-Point Data Generation for GUI Agents [52.22377425487]
  End-to-end GUI agents for real desktop environments require large amounts of high-quality interaction data.<n>We present a trajectory expansion framework Anchor that bootstraps scalable desktop supervision from a small set of verified seed demonstrations.<n>Experiments on standard desktop benchmarks, OSWorld and WindowsAgentArena, show that models fine-tuned on our expanded corpus achieve consistent improvements.
  arXiv  Detail & Related papers  (2026-02-06T19:55:26Z)
• InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents [36.740230738304525]
  InfiAgent keeps the agent's reasoning context strictly bounded regardless of task duration.<n>InfiAgent with a 20B open-source model is competitive with larger proprietary systems.
  arXiv  Detail & Related papers  (2026-01-06T17:35:57Z)
• NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents [79.29376673236142]
  Existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems.<n>We present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents.
  arXiv  Detail & Related papers  (2025-12-14T15:12:13Z)
• AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management [24.465443389008055]
  AgentProg is a program-guided approach for agent context management.<n>It reframes the interaction history as a program with variables and control flow.<n> Experiments on AndroidWorld and our extended long-horizon task suite demonstrate that AgentProg has achieved the state-of-the-art success rates.
  arXiv  Detail & Related papers  (2025-12-11T07:37:38Z)
• MAPLE: A Mobile Agent with Persistent Finite State Machines for Structured Task Reasoning [46.18718721121415]
  We present MAPLE, a state-aware multi-agent framework that abstracts app interactions as a Finite State Machine (FSM)<n>We computationally model each UI screen as a discrete state and user actions as transitions, allowing the FSM to provide a structured representation of the app execution.<n> MAPLE consists of specialized agents responsible for four phases of task execution: planning, execution, verification, error recovery, and knowledge retention.
  arXiv  Detail & Related papers  (2025-05-29T16:08:51Z)

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.