LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Hugging Face Daily Papers Papers
llm-agents long-horizon task-state harness benchmark research

Summary

Introduces LongHorizon-Harness, a task-state management approach for long-horizon LLM agents using a Manage-Execute-Audit loop, showing consistent improvements across models and benchmarks like WeaveBench and OSWorld.

Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, existing agent harnesses maintain task execution, task state, and completion assessment within a growing context, making the state difficult to track and allowing incorrect self-assessments to propagate into later decisions. We reformulate long-horizon execution as a task-state management problem and propose LongHorizon-Harness, which maintains the task state explicitly outside execution and updates it only with facts independently verified from the environment. Its Manage-Execute-Audit(MEA) loop uses a manager to maintain the task state and determine the next subtask, a fresh-context executor to perform it, and a read-only auditor to verify the resulting environment state before the next round. A lightweight AgentAdapter supports interchangeable model and harness backends without modifying their native agent loops. LongHorizon-Harness improves Qwen~3.7-Plus from 51.8% to 80.7% on WeaveBench, from 69.7% to 77.2% on Terminal-Bench~2.1, and from 2.8% to 8.3% on OSWorld~2.0. It also raises Claude Opus~4.7 from 20.0% to 34.3% on an OSWorld2.0 subset, demonstrating consistent gains across models, harnesses, and interaction domains.
Original Article
View Cached Full Text

Cached at: 08/04/26, 09:38 AM

Paper page - LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Source: https://huggingface.co/papers/2608.01964

Abstract

Largelanguagemodel(LLM)agentsincreasinglyundertakelong-horizontasksthatrequiresustainedreasoning,tooluse,andrevisionacrossmanyinterdependentsteps.However,existingagentharnessesmaintaintaskexecution,taskstate,andcompletionassessmentwithinagrowingcontext,makingthestatedifficulttotrackandallowingincorrectself-assessmentstopropagateintolaterdecisions.Wereformulatelong-horizonexecutionasatask-statemanagementproblemandproposeLongHorizon-Harness,whichmaintainsthetaskstateexplicitlyoutsideexecutionandupdatesitonlywithfactsindependentlyverifiedfromtheenvironment.ItsManage-Execute-Audit(MEA)loopusesamanagertomaintainthetaskstateanddeterminethenextsubtask,afresh-contextexecutortoperformit,andaread-onlyauditortoverifytheresultingenvironmentstatebeforethenextround.AlightweightAgentAdaptersupportsinterchangeablemodelandharnessbackendswithoutmodifyingtheirnativeagentloops.LongHorizon-HarnessimprovesQwen~3.7-Plusfrom51.8%to80.7%onWeaveBench,from69.7%to77.2%onTerminal-Bench~2.1,andfrom2.8%to8.3%onOSWorld~2.0.ItalsoraisesClaudeOpus~4.7from20.0%to34.3%onanOSWorld2.0subset,demonstratingconsistentgainsacrossmodels,harnesses,andinteractiondomains.

View arXiv pageView PDFProject pageGitHub51Add to collection

Get this paper in your agent:

hf papers read 2608\.01964

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.01964 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.01964 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.01964 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Hugging Face Daily Papers

OneDayAgent is a long-horizon harness for autonomous agents that decomposes open-ended tasks into bounded subtasks, manages execution memory under context pressure, and verifies/repairs final outputs. It achieves state-of-the-art results on AgentIF-OneDay with GLM-5.2 and generalizes across five backend LLMs.

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents

arXiv cs.LG

Introduces EvoHarness-RL, a framework that learns runtime harness policies for long-horizon LLM agents, enabling them to construct and update external state (belief, progress, experience) during task execution. Using Qwen3-8B on ALFWorld, it achieves 96.9% success and reveals harness annealing and evolution dynamics.

Self-Harness: Harnesses That Improve Themselves

Hacker News Top

Self-Harness introduces a new paradigm where LLM-based agents iteratively improve their own operating harness by mining model-specific weaknesses, proposing harness modifications, and validating them through regression testing, achieving substantial performance gains on Terminal-Bench-2.0 across multiple base models.