arXiv 2610.32253 · cs.AI · 2026-10-23
RSIHub: A Composable Framework for Agent-Evolution Methods
Zimu Wang, Xiaobo Wang, Siyu Ye, Jiaqi Li, Silin Chen, Yuling Shi, Ruobing Wang, Jingjing Zhang 等 14 人
ByteDance
一句话要点
RSIHub框架通过可组合的组件设计,支持多种智能体进化方法在共享基础设施上高效对比与迭代,最大提升达13.5个百分点,但性能迁移存在差异。
RSIHub enables composable, comparable agent evolution methods with up to 13.5pp improvement, though gains vary across tasks.
要点
- 智能体进化方法常因重复构建实验流程而效率低下,RSIHub通过共享基础设施和可组合组件解决这一问题。
- 框架支持将不同进化策略(如AHE、Hyperagents等)封装为可复用的recipe,无需修改核心代码即可快速部署与对比。
- 在MiniSWE和Codex上的实验显示,最优方法在Terminal Bench 2和τ³ Banking上提升达13.5个百分点,但性能在不同任务间迁移不稳定。
- RSIHub提供统一的评估协议和可追溯的候选历史,为智能体进化方法的开发与比较提供了标准化、可复现的平台。
English overview
RSIHub is a composable, open-source framework that enables researchers to build, compare, and extend agent evolution methods using reusable recipes and shared infrastructure. It supports multiple methods like AHE and Hyperagents without core modifications, offering standardized evaluation, lineage tracking, and component reusability. Experiments on MiniSWE and Codex show up to 13.5 percentage point gains in pass@1, though performance transfer across tasks is inconsistent.
只根据 arXiv 官方摘要,由开源模型整理,经数字/专名自动核对(必须在摘要中出现),以论文原文为准。
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题:智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
同主题:评测与数据
- Spectral-Spatial Interpretation 2026-10-15 · ▲753
- StreamEval: Evaluating Interactive Streaming Video Generation Models 2026-10-20 · ▲649
- Has GPT-6-Astra Achieved Embodied Intelligence? 2026-10-15 · ▲421
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations 2026-10-01 · ▲287
- FDE-Gym: The Last Mile of AI Delivery 2026-10-15 · ▲270
同机构:ByteDance
- Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation 2026-10-22
- DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal 2026-10-19
- Cortex: Consolidating Context into Parametric Memory 2026-10-14
- DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding 2026-10-14
- DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation 2026-10-02
数据说明
元数据来自 arXiv API(已核实);点赞来自 Hugging Face 每日论文;引用来自 Semantic Scholar。最近刷新 2026-10-23。
要点由本站根据摘要自写,不转载摘要原文,请阅读原文。