Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training

• URL: http://arxiv.org/abs/2607.27929v1
• Date: Thu, 30 Jul 2026 09:41:08 GMT
• Title: Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training
• Abstract summary: Training terminal agents at scale requires diverse, verifiable terminal tasks and high-quality interaction trajectories.<n>Existing methods face two key limitations: weak reliability caused by the disconnect between task generation and real execution.<n>We propose Meta-Task, a framework that redefines terminal task synthesis as a Terminal-Bench-format task itself.
• Score: 13.580418686043815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training terminal agents at scale requires diverse, verifiable terminal tasks and high-quality interaction trajectories, yet acquiring such data remains a significant challenge. Existing synthesis methods face two key limitations: (1) weak reliability caused by the disconnect between task generation and real execution, and (2) limited diversity and scalability due to dependence on existing repositories. We propose Meta-Task, a framework that redefines terminal task synthesis as a Terminal-Bench-format task itself: an agent operates within a real container environment to iteratively generate, execute, and verify tasks, so that synthesized components are checked for internal consistency and executability within the generation loop itself. Building upon this, we decouple the target task requirements along multiple dimensions, introduce a multi-phase mechanism that dynamically designs novel task specifications before producing the actual tasks, and incorporate optional external material support to enhance diversity and realism. We additionally apply LLM-as-Judge filtering to ensure the quality of the final training data. Experiments on Terminal-Bench 2.0 show that fine-tuning on only 3,221 Meta-Task synthesized trajectories achieves 22.5% and 31.8% Avg Pass@1 for Qwen3-14B and Qwen3-32B respectively, outperforming concurrent approaches with significantly less training data.

Related papers

• Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments [89.86581796261123]
  We introduce Terminal-Universe, a framework which turns each trajectory into a reusable environment.<n>Terminal-Universe replays the file operations recorded in a trajectory to restore each file before the agent modified it, yielding a partial workspace.<n>We also scale the tasks along two axes: breadth and depth.
  arXiv  Detail & Related papers  (2026-09-03T17:41:05Z)
• FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis [37.074035615771066]
  FACET (Fine-grained Agentic Construction of Executable Tasks) is a framework that addresses both information preservation and cross-artifact consistency.<n>It reconstructs related agent skills into coherent, information-rich scenarios, then realizes and repairs the execution environment.<n>It produces complex terminal tasks with dense executable checks, and successful trajectories collected from these tasks provide effective, data-efficient supervision.
  arXiv  Detail & Related papers  (2026-08-19T06:19:20Z)
• CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents [40.27594136040026]
  We introduce CLI-Universe, a synthesis engine that constructs terminal-agent tasks.<n>We instantiate a dataset of 6,000 trajectories called CLI-Universe-6K.<n>Remarkably, fine-tuning Qwen3-32B on CLI-Universe-6K achieves 33.4% on Terminal-Bench 2.0.
  arXiv  Detail & Related papers  (2026-06-22T05:50:23Z)
• Terminal-World: Scaling Terminal-Agent Environments via Agent Skills [52.39713754337834]
  We introduce Terminal-World, a fully automated pipeline that uses agent skills as the central synthesis primitive.<n>We construct 5,723 training environments and train Terminal-World-8B/14B/32B, evaluated across 6 benchmarks.<n>Terminal-World-32B surpasses Nemotron-Terminal-32B on Terminal-Bench 2.0 by +4.5 Pass@1 (31.5) and achieves 43.8 Pass@3.
  arXiv  Detail & Related papers  (2026-05-20T08:14:51Z)
• Toward Scalable Terminal Task Synthesis via Skill Graphs [16.33536290621557]
  Terminal agents have demonstrated strong potential for autonomous command-line execution, yet their training remains constrained by the scarcity of high-quality and diverse execution trajectories.<n>We present Skill Synth, an automated framework for terminal task synthesis built on a scenario-mediated skill graph.
  arXiv  Detail & Related papers  (2026-04-28T14:53:59Z)
• TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents [70.68963723787424]
  TermiGen is an end-to-end pipeline for synthesizing verifiable environments and resilient expert trajectories.<n>Our TermiGen-Qwen2.5-Coder-32B achieves a 31.3% pass rate on TerminalBench.
  arXiv  Detail & Related papers  (2026-02-06T23:56:50Z)
• Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments [36.81059045059001]
  Training agentic models for terminal-based tasks depend on high-quality terminal trajectories that capture realistic long-horizon interactions.<n>We propose textbfTerminalTraj, a scalable pipeline that generates Docker-aligned task instances and synthesizes agent trajectories with executable validation code.<n>Using TerminalTraj, we curate 32K Docker images and generate 50,733 verified terminal trajectories across eight domains.
  arXiv  Detail & Related papers  (2026-02-01T14:09:23Z)
• Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents [52.30603055218294]
  Trajectory2Task is a verifiable data generation pipeline for studying tool use at scale under three realistic user scenarios.<n>It converts valid tool-call trajectories into user-facing tasks with controlled intent adaptations.<n>We benchmark seven state-of-the-art LLMs on the generated complex user scenario tasks and observe frequent failures.
  arXiv  Detail & Related papers  (2026-01-28T00:36:13Z)
• Task Indicating Transformer for Task-conditional Dense Predictions [16.92067246179703]
  We introduce a novel task-conditional framework called Task Indicating Transformer (TIT) to tackle this challenge. Our approach designs a Mix Task Adapter module within the transformer block, which incorporates a Task Indicating Matrix through matrix decomposition. We also propose a Task Gate Decoder module that harnesses a Task Indicating Vector and gating mechanism to facilitate adaptive multi-scale feature refinement.
  arXiv  Detail & Related papers  (2024-03-01T07:06:57Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies [57.27944046925876]
  We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph. Instead of directly learning a meta-policy, we develop a Meta-learner with Subtask Graph Inference. Our experiment results on two grid-world domains and StarCraft II environments show that the proposed method is able to accurately infer the latent task parameter.
  arXiv  Detail & Related papers  (2020-01-01T17:34:00Z)

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.