RSIHub:一個用於 Agent 演化方法的可組合框架
RSIHub: A Composable Framework for Agent-Evolution Methods
RSIHub 是一個開源框架,為 Agent 演化研究提供共用基礎設施,讓研究人員建構、比較及擴展相關方法。研究以 MiniSWE 和 Codex,在 Terminal Bench 2 與 τ^3 Banking 上進行評估,觀察到的最高整體 pass@1 提升為 13.5 個百分點;不同設定下的方法排名有所不同,優化所得增益亦未必能延伸至留出任務。
Published on Oct 23
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
RSIHub is an open-source framework that standardizes agent-evolution research by providing shared infrastructure for building, comparing, and extending methods with reusable components and consistent evaluation.
Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an open-source framework for building, comparing, and extending these methods on shared infrastructure. Recipes compose reusable operators and declare mutable resources; RSIHub supplies execution, evaluation, recovery, and lineage. Researchers can focus on evolution policy while evaluation stays outside the mutable surface and results remain tied to candidates and evaluation conditions. We instantiate AHE, Hyperagents, A-Evolve, and GEPA without modifying the framework core, keeping method-specific logic in recipes and operators. We evaluate them with MiniSWE and Codex on Terminal Bench 2 and τ^3 Banking under fixed model and evaluator configurations. The largest observed overall pass@1 gain is 13.5 percentage points, while method rankings vary across settings and optimization gains do not always transfer to held-out tasks. RSIHub provides a common protocol for comparing evolution policies, inspectable candidate histories, and reusable components for developing new methods.
View arXiv page View PDF Project page GitHub 186 Add to collection
Get this paper in your agent:
hf papers read 2610.32253
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/2610.32253 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/2610.32253 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/2610.32253 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