跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-20AI 評分38

RiseHarness 如何提升長時程終端智能體的可靠性

Harness Self-Evolution for Long-Horizon Terminal Agents

AI 導讀

RiseHarness 透過分析執行軌跡、整合其他框架的機制,迭代改進智能體 harness 的可靠性,同時固定模型權重。它以同一設定下成功與失敗的執行作比較,結合運行時監控器記錄的 harness 內部追蹤,找出跨任務反覆出現的問題。論文評估任務成功率與可靠性,並測試改進能否遷移至未見過的基準測試。

正文

Published on Oct 20

Authors:

,

,

,

,

,

,

,

Abstract

RiseHarness iteratively improves agent harness reliability by analyzing execution traces and integrating mechanisms from other frameworks without altering model weights.

Long-horizon terminal agents may solve a task in one run yet fail across repeated runs. Stochastic errors can propagate through actions and context, creating a gap between capability and reliable execution. We present RiseHarness, a framework for iteratively improving agent harnesses with model weights fixed. It focuses on flipping tasks with both successful and failed runs under the same configuration, using successful runs as references for failure analysis. RiseHarness combines agent trajectories with internal harness traces from a runtime monitor to examine how model actions interact with command execution, feedback, context management, and completion decisions. A Harness Handbook links this evidence to harness behaviors and source code, helping identify recurring problems in mechanisms shared across tasks. RiseHarness then searches other harness frameworks for relevant implementations and adapts them as design references to the current model and execution protocol. Candidate changes undergo behavioral checks and repeated task evaluation; versions with measured gains seed the next iteration. This loop integrates suitable mechanisms from different frameworks into a single harness and uses new execution evidence to guide further changes. We evaluate task success and reliability across models, ablate harness execution evidence and external research, and test transfer to unseen benchmarks with the same model. RiseHarness treats a specific model as the unit of harness adaptation, studying how changes to shared interaction mechanisms can make existing capabilities more reliable across tasks.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.27435

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.27435 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.27435 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.27435 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co