FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis
Summary
FACET is a framework for synthesizing high-quality terminal tasks for AI agent training by preserving source intent and ensuring cross-artifact consistency, leading to improved performance on Terminal-Bench 2.1.
View Cached Full Text
Cached at: 08/20/26, 04:04 AM
Paper page - FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis
Source: https://huggingface.co/papers/2608.18580 Authors:
,
,
,
,
,
,
,
,
,
,
,
Abstract
FACET constructs executable terminal tasks by preserving source intent and grounding instructions, solutions, and verifiers in a shared repaired environment to enable scalable agent training.
Trainingterminal agentsrequires scalableexecutable supervision, yet synthesizing high-quality terminal tasks remains challenging. Each task couples an instruction, an initialized environment, a reference solution, and an executable verifier; if these artifacts are generated from inconsistent assumptions, the resulting task may be unsolvable or incorrectly evaluated. Meanwhile, multi-stage synthesis can discard the goals, dependencies, state transitions, and procedural constraints encoded in the original sources. We present FACET (Fine-grained Agentic Construction of Executable Tasks), a framework that addresses both information preservation andcross-artifact consistency. FACET reconstructs relatedagent skillsinto coherent, information-rich scenarios, then realizes and repairs theexecution environmentbefore generating the final task artifacts. The resultingcontainer stateserves as shared grounding for the instruction, solution, and verifier, whileexecution-based validationand targeted repair correct artifact-specific failures without unnecessarily regenerating valid components. FACET produces complex terminal tasks with dense executable checks, and successful trajectories collected from these tasks provide effective, data-efficient supervision. Fine-tuning models across multiple scales consistently improves performance onTerminal-Bench 2.1, while analyses of alternative generation schemes support the importance of environment-grounded construction for task validity and solution-verifier alignment. These results establishsource-intent preservationandshared executable-state groundingas key principles for scalable terminal-task synthesis.
View arXiv pageView PDFProject pageGitHub2Add to collection
Get this paper in your agent:
hf papers read 2608\.18580
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/2608.18580 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.18580 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.18580 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
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
LiteCoder-Terminal-Gen introduces a zero-dependency synthetic pipeline that generates executable terminal training environments, producing SFT and RL datasets that enable language agents to achieve significant performance gains on Terminal Bench benchmarks.
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
Terminal-World introduces a fully automated pipeline that uses agent skills to synthesize high-quality training data for terminal agents, enabling models to outperform baselines with only 1.2% of the training data. The method co-derives task instructions, environments, and teacher trajectories from skill primitives.
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
CLI-Universe is a synthesis engine that generates verifiable terminal-agent tasks via multi-dimensional capability taxonomy and evidence-guided research, producing a distilled dataset of 6,000 trajectories. Fine-tuning Qwen3-32B on this dataset achieves 33.4% on Terminal-Bench 2.0, setting a new state-of-the-art for open-source models at or below 32B parameters.
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Terminal-Universe is a framework that reconstructs executable workspaces from agent trajectories to synthesize diverse training tasks, improving AI agent post-training performance through supervised fine-tuning.
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
TACO introduces a self-evolving compression framework that automatically learns to shrink redundant terminal interaction history, cutting token overhead ~10% while boosting accuracy 1-4% across TerminalBench and other code-agent benchmarks.