AI News AI资讯 15h ago Updated 2h ago 更新于 2小时前 48

Iris-mini and Iris-pro are the strongest open-weight search agents in their class Iris-mini 和 Iris-pro 是同类中最强的开源搜索智能体

AllSpark released Iris-mini (35B) and Iris-pro (397B) as open-source search agents built on Qwen-series models, with full training recipes and code on Hugging Face and GitHub. Training data is reverse-engineered from web link structures, generating multi-step reasoning tasks where paraphrasing prevents simple text-search solutions, ensuring genuine reasoning over lookup. A two-stage filtering pipeline using a teacher model and a data-derived judge model, combined with SFT-RL climbing against liv AllSpark发布Iris-mini(35B参数)和Iris-pro(397B参数)两个开源搜索智能体,附带完整训练配方与代码 训练数据通过反向工程网页链接结构生成,问题设计强制模型进行多步推理而非简单搜索 上下文管理对性能影响巨大,小模型Boost可达21.2分,揭示现有基准测试可能被外部脚手架污染 在BrowseComp、DeepSearchQA、Humanity's Last Exam四大基准上,Iris系列在各自规模类别中表现最强 搜索训练带来意外泛化效果,提升未训练的通用工具使用和办公任务表现

65
Hot 热度
72
Quality 质量
68
Impact 影响力

Analysis 深度分析

TL;DR

  • AllSpark released Iris-mini (35B) and Iris-pro (397B) as open-source search agents built on Qwen-series models, with full training recipes and code on Hugging Face and GitHub.
  • Training data is reverse-engineered from web link structures, generating multi-step reasoning tasks where paraphrasing prevents simple text-search solutions, ensuring genuine reasoning over lookup.
  • A two-stage filtering pipeline using a teacher model and a data-derived judge model, combined with SFT-RL climbing against live web search, produces the final agents.
  • Context management during inference has a dramatically larger impact on benchmark scores—especially for smaller models—raising questions about how much of reported performance reflects model capability versus scaffolding.
  • Search training yields unexpected generalization benefits, improving performance on unrelated tool use and office work tasks, suggesting search may be a foundational rather than narrow skill.

Why It Matters

This release provides one of the most complete open-source packages for building search agents to date, including models, training data construction methodology, evaluation harness, and reinforcement learning pipelines. It also surfaces a critical methodological concern: many published search agent benchmarks may conflate model quality with context-management tricks, which has direct implications for how the community evaluates and compares agentic systems. The unexpected cross-domain improvements from search training further challenge the assumption that search is a narrow capability.

Technical Details

  • Model architecture: Iris-mini (35B parameters, based on Qwen3.6-35B-A3B) and Iris-pro (397B parameters, based on Qwen3.5-397B-A17B), both supporting a 256,000-token context window.
  • Training data construction: Tasks are generated by traversing web page link graphs from seed pages, creating multi-step questions that require chaining reasoning across connected terms. Every intermediate term is paraphrased to prevent trivial text search, and a reference model filter ensures only questions solvable with tools but not without them are included.
  • Two-stage filtering and SFT-RL climbing: A stronger teacher model generates solution paths (reasoning + queries + results), which are filtered for correctness, repetition loops, and search depth. A judge model with data-derived criteria performs step-by-step review. Supervised fine-tuning and reinforcement learning alternate iteratively, with the hardest solved tasks and most efficient paths feeding back into each cycle. All inference runs internally on the team's own Qwen model, avoiding external service dependency.
  • Context management strategy: The Iris Harness includes history-discard techniques and a second-attempt mechanism where failed runs are condensed into notes recording what was checked and ruled out, appended to subsequent attempts. This significantly boosts smaller models by mitigating faster context consumption.
  • Benchmark results (with context management enabled): Iris-mini scored 82.2 on BrowseComp, 84.8 on BrowseComp-ZH, 86.9 on DeepSearchQA, and 52.3 on Humanity's Last Exam. Iris-pro scored 88.6, 85.1, 92.9, and 56.4 respectively. Context management boosted Iris-mini's BrowseComp score by up to 21.2 points.

Industry Insight

  • Benchmark reporting standards for search agents need revision: the dramatic gap between scored results with and without context management suggests the community should mandate paired evaluations that isolate model capability from engineering scaffolding, or risk inflating perceived progress.
  • The cross-task generalization from search training (tool use, office work) suggests that investing in search as a foundational agent skill could yield broader ROI than treating it as a standalone module, influencing how teams allocate training budgets and design curricula.
  • The open release of training recipes, data construction pipelines (planned), and an evaluation harness compatible with any OpenAI-endpoint lowers the barrier for independent replication and comparison, likely accelerating the open-weight search agent ecosystem and putting pressure on proprietary systems to match transparency.

TL;DR

  • AllSpark发布Iris-mini(35B参数)和Iris-pro(397B参数)两个开源搜索智能体,附带完整训练配方与代码
  • 训练数据通过反向工程网页链接结构生成,问题设计强制模型进行多步推理而非简单搜索
  • 上下文管理对性能影响巨大,小模型Boost可达21.2分,揭示现有基准测试可能被外部脚手架污染
  • 在BrowseComp、DeepSearchQA、Humanity's Last Exam四大基准上,Iris系列在各自规模类别中表现最强
  • 搜索训练带来意外泛化效果,提升未训练的通用工具使用和办公任务表现

为什么值得看

本文揭示了搜索智能体训练中的关键洞察:上下文管理往往比模型本身差异更能决定基准分数,这对评估开源Agent性能提出了新的方法论要求。同时,自动化训练数据构建方案提供了低成本获取高质量推理数据的新路径。

技术解析

  • 模型规格与基准表现:Iris-mini(35B,基于Qwen3.6-35B-A3B)和Iris-pro(397B,基于Qwen3.5-397B-A17B)均支持256K上下文窗口。带上下文管理时,Iris-mini在BrowseComp/BrowseComp-ZH/DeepSearchQA/HLE上分别获82.2/84.8/86.9/52.3分,Iris-pro获88.6/85.1/92.9/56.4分。

  • 数据构建方法:从种子页面出发沿出链构建词项关系图,生成需多步链式推理的问题。所有中间节点替换为改写表述,确保答案无法通过简单文本匹配获得,迫使模型真正推理。

  • 两阶段过滤机制:强教师模型生成完整解题路径(推理+搜索查询+结果),第一轮过滤检查路径正确性、重复循环和搜索深度,第二轮由基于数据自动推导标准的评审模型进行逐步审查。

  • SFT-RL交替训练:监督微调与强化学习交替迭代,强化学习阶段连接实时网页搜索。评审模型和结果摘要均运行在训练集群内部,不依赖外部服务。

  • 上下文管理策略:提出历史丢弃(history discarding)方法——首次尝试失败后生成简短记录(已探索路径与排除项),追加至任务供第二次尝试,有效缓解小模型上下文消耗过快问题。

行业启示

  • 当前开源Agent基准测试可能存在系统性偏差:上下文管理等外部基础设施对性能贡献巨大,报告结果难以剥离模型能力与脚手架效果,建议建立更严格的对照评估标准。
  • 搜索能力可能是一项"基础技能"而非窄领域专项:训练数据和方法带来的泛化效应表明,搜索训练有助于处理任何需要利用不完整信息完成任务的场景。
  • 自动化数据构建结合两阶段过滤是可行的低成本高质量数据生产范式,为其他Agent类型(如工具使用、代码生成)的数据方案提供参考。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Open Source 开源 Agent Agent LLM 大模型 Benchmark 基准测试 Research 科学研究