upgrade v0.2.0

config/_default/menus.yaml

@@ -17,6 +17,11 @@ main:
   - name: Community
     url: community/
     weight: 50
+  - name: Paper
+    url: "https://arxiv.org/abs/2608.16185"
+    weight: 55
+    params:
+      external: true
 
 sidebar:
   - identifier: more

config/_default/menus.zh.yaml

@@ -16,6 +16,11 @@ main:
   - name: 社区
     url: community/
     weight: 50
+  - name: 论文
+    url: "https://arxiv.org/abs/2608.16185"
+    weight: 55
+    params:
+      external: true
 
 sidebar:
   - identifier: more

content/_index.md

@@ -17,10 +17,10 @@ sections:
         url: docs/getting-started/
         icon: rocket-launch
       secondary_action:
-        text: Read the Technical Report
-        url: blog/technical-deep-dive/
+        text: Read the Paper
+        url: https://arxiv.org/abs/2608.16185
       announcement:
-        text: "Sirchmunk v0.0.8 — Knowledge Compile (Beta), DEEP Mode Generalization & I/O Optimization"
+        text: "Sirchmunk v0.2.0 — LENS Paper on arXiv · Multi-Path DEEP Retrieval · Large Corpus Robustness"
         link:
           text: "View all releases"
           url: "https://github.com/modelscope/sirchmunk/releases"
@@ -62,22 +62,22 @@ sections:
       items:
         - name: Embedding-Free Retrieval
           icon: magnifying-glass
-          description: "Work directly with raw data. No vector database, no pre-indexing, no ETL pipeline. Just drop your files and search immediately."
+          description: "Work directly with raw data — no vector database, no pre-indexing, no ETL pipeline. Drop your files and search immediately with full source fidelity."
         - name: Self-Evolving Knowledge
           icon: arrow-path
-          description: "Knowledge clusters compound with every search. The system learns and improves over time, delivering faster and richer results."
-        - name: Monte Carlo Evidence Sampling
+          description: "Every search produces a reusable KnowledgeCluster. Clusters merge, broaden, and form meta-communities over time — the system literally gets smarter as you use it."
+        - name: "LENS: Latent Evidence Exploration"
           icon: chart-bar
-          description: "Strategically sample documents using exploration-exploitation methods. Extract precise evidence without reading entire files."
-        - name: ReAct Agent Fallback
+          description: "Budgeted evidence localization over a query-conditioned latent evidence space. The LENS framework locates source-grounded evidence from raw dynamic documents under explicit cost constraints."
+        - name: Multi-Path DEEP Retrieval
           icon: cpu-chip
-          description: "When standard retrieval falls short, an autonomous ReAct agent iteratively explores alternative strategies until answers are found."
+          description: "Parallel lexical, entity, directory, structural, and topic-graph retrieval routes fused by confidence-weighted RRF — with soft route-collapse for high-confidence single-file lookups."
+        - name: Large Corpus Robustness
+          icon: shield-check
+          description: "Bounded per-file and per-query retrieval cost: tiered rg-first scan, adapter whitelist, file-size cap, per-file match limits, and hard token budgets keep huge corpora fast."
         - name: Multi-Surface Integration
           icon: globe-alt
-          description: "MCP protocol, OpenClaw skill, REST API, WebSocket real-time chat, CLI, and a modern Web UI — all built in."
-        - name: Token-Efficient Design
-          icon: bolt
-          description: "LLM inference triggered only when necessary. Monte Carlo sampling and knowledge reuse minimize costs while maximizing intelligence."
+          description: "MCP protocol, OpenClaw skill, REST API, WebSocket real-time chat, CLI, and a modern Web UI with knowledge graph visualization — all built in."
   - block: cta-card
     content:
       title: "Start Searching with Sirchmunk"

content/_index.zh.md

@@ -17,10 +17,10 @@ sections:
         url: docs/getting-started/
         icon: rocket-launch
       secondary_action:
-        text: 阅读技术报告
-        url: blog/technical-deep-dive/
+        text: 阅读论文
+        url: https://arxiv.org/abs/2608.16185
       announcement:
-        text: "Sirchmunk v0.0.8 — 知识编译（Beta）、DEEP 模式泛化增强与 I/O 优化"
+        text: "Sirchmunk v0.2.0 — LENS 论文已发布 · 多路 DEEP 检索 · 大语料鲁棒性"
         link:
           text: "查看所有版本"
           url: "https://github.com/modelscope/sirchmunk/releases"
@@ -62,22 +62,22 @@ sections:
       items:
         - name: 无嵌入检索
           icon: magnifying-glass
-          description: "直接处理原始数据。无需向量数据库、无需预索引、无需 ETL 管线。只需放入文件即可立即搜索。"
+          description: "直接处理原始数据 — 无需向量数据库、无需预索引、无需 ETL 管线。放入文件即可搜索，完整保留源数据保真度。"
         - name: 自进化知识
           icon: arrow-path
-          description: "知识簇随每次搜索不断积累。系统持续学习与改进，搜索结果越来越快、越来越丰富。"
-        - name: 蒙特卡洛证据采样
+          description: "每次搜索都生成可复用的 KnowledgeCluster。聚类随使用不断合并、拓展并形成元社区 — 系统在使用中持续变得更聪明。"
+        - name: "LENS：隐式证据探索"
           icon: chart-bar
-          description: "使用探索-利用策略对文档进行智能采样，无需阅读整个文件即可提取精确证据。"
-        - name: ReAct 智能体自适应检索
+          description: "在查询条件下的隐式证据空间中进行预算约束证据定位。LENS 框架在显式成本约束下从原始动态文档中定位源可追溯证据。"
+        - name: 多路 DEEP 检索
           icon: cpu-chip
-          description: "当常规检索不足时，ReAct 智能体自主迭代推理并探索替代检索策略，直到找到答案。"
+          description: "词法、实体、目录、结构与主题图多条并行检索路径，通过置信度加权 RRF 融合 — 高置信单文件查询触发 soft 路由收缩快通道。"
+        - name: 大语料鲁棒性
+          icon: shield-check
+          description: "单文件与单次查询的检索成本均设界：rg 优先分层扫描、适配器白名单、文件大小上限、单文件匹配上限与硬 token 预算，确保大规模语料高效稳定。"
         - name: 多接口集成
           icon: globe-alt
-          description: "MCP 协议、OpenClaw 技能，REST API、WebSocket 实时聊天、CLI 与现代 Web UI — 全部内置。"
-        - name: Token 高效设计
-          icon: bolt
-          description: "仅在必要时触发 LLM 推理。蒙特卡洛采样和知识复用最大程度降低成本，同时最大化智能。"
+          description: "MCP 协议、OpenClaw 技能、REST API、WebSocket 实时聊天、CLI 与知识图谱可视化的现代 Web UI — 全部内置。"
   - block: cta-card
     content:
       title: "开始使用 Sirchmunk 搜索"

content/blog/in-context-search/index.md

@@ -18,6 +18,8 @@ image:
 
 With the evolution of RAG (Retrieval-Augmented Generation) technology, a new paradigm called **In-Context Search (ICS)** is redefining how LLMs interact with external knowledge. This post compares traditional Graph-based RAG with next-generation ICS approaches represented by **[PageIndex](https://github.com/VectifyAI/PageIndex)** and **[Sirchmunk](https://github.com/modelscope/sirchmunk)**.
 
+**Update (September 2026):** The theoretical foundations described in this article have been formalized in our research paper: [LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents](https://arxiv.org/abs/2608.16185) (arXiv:2608.16185).
+
 <!--more-->
 
 ### Abstract
@@ -47,8 +49,8 @@ The industry is now pivoting toward **In-Context Search (ICS)**. In this paradig
 | Dimension | **LightRAG** (Advanced Graph-RAG) | **PageIndex** (Reasoning-based ICS) | **Sirchmunk** (Indexless / Self-Evolving) |
 | --- | --- | --- |-------------------------------------------|
 | **Architectural Philosophy** | Index-Centric (Graph Topologies) | Reasoning-Centric (Hierarchical ICS) | Agile-Centric (Raw Search & Evolution)    |
-| **Primary Mechanism** | Dual-level Graph Traversal | Agentic Tree Navigation | Greedy Cascade (FAST) / Monte Carlo Sampling (DEEP) |
-| **Retrieval Depth** | Global & Local via Graph Edges | Structural Pathfinding | Statistical Importance Extraction         |
+| **Primary Mechanism** | Dual-level Graph Traversal | Agentic Tree Navigation | Multi-path DEEP Retrieval (5 paths) / Greedy Cascade (FAST) |
+| **Retrieval Depth** | Global & Local via Graph Edges | Structural Pathfinding | Confidence-weighted RRF Fusion + Statistical Importance Extraction |
 | **Indexing Overhead** | High (Graph Construction) | Moderate (Tree Metadata) | **Minimal to Zero**                       |
 | **Context Fidelity** | High (Entity-Relationship) | **Maximum** (Structural Integrity) | **Full Fidelity** (Raw Data Access)       |
 | **Data Freshness** | Low (Re-indexing required) | Moderate (Incremental updates) | **Real-time** (Direct File Access)        |
@@ -101,9 +103,9 @@ PageIndex implements an **Agentic Loop** that mimics human research patterns—n
 
 Sirchmunk represents the **"Agile Hunter"** philosophy in the In-Context Search (ICS) landscape. It prioritizes **data freshness** and **operational speed**, completely bypassing the static tree-building phase. Instead, it treats the file system as a live, queryable environment, leveraging statistical mechanics and agentic reflection.
 
-Sirchmunk operates in two distinct search modes. **FAST mode** (default) employs a greedy strategy with 2-level keyword cascade and context-window sampling, achieving retrieval in 2–5 seconds with only 2 LLM calls — a **~10x speedup** over the comprehensive mode. **DEEP mode** activates the full Monte Carlo evidence sampling pipeline with multi-round ReAct refinement for maximum recall on complex queries (10–30 seconds).
+Sirchmunk operates in two distinct search modes. **FAST mode** employs a greedy strategy with 2-level keyword cascade and context-window sampling, achieving retrieval in 2–5 seconds with only 2 LLM calls — a **~10x speedup** over the comprehensive mode. **DEEP mode** (default since v0.1.0) runs five complementary retrieval paths (lexical, entity, directory, structural, topic-graph) fused via confidence-weighted Reciprocal Rank Fusion, followed by Monte Carlo evidence sampling and multi-round ReAct refinement for maximum recall on complex queries (10–30 seconds).
 
-As of v0.0.6post1, Sirchmunk also ships as an OpenClaw skill — enabling any OpenClaw-compatible agent to invoke its search capability via natural language. From v0.0.6 onward, the stack further includes **multi-turn conversation** with context management, **document summarization**, and **cross-lingual retrieval** alongside the FAST/DEEP search modes above.
+As of v0.2.0, Sirchmunk also ships as an OpenClaw skill — enabling any OpenClaw-compatible agent to invoke its search capability via natural language. The stack includes **multi-turn conversation** with context management, **document summarization**, and **cross-lingual retrieval** alongside the FAST/DEEP search modes above.
 
 ---
 
@@ -155,7 +157,20 @@ Sirchmunk utilizes a "Post-hoc Indexing" strategy. It doesn't index before you a
 | **Just-in-Time Indexing** | Builds a dynamic map of data based on actual usage patterns. | Python-Native |
 | **Knowledge Reuse** | Hits the cache for similar future queries, evolving from brute-force to high-speed retrieval. | DuckDB SQL |
 
-Through this mechanism, Sirchmunk evolves from a "brute-force hunter" into a "sophisticated librarian" organically, without the maintenance overhead of traditional pre-indexed databases.
+Through this mechanism, Sirchmunk evolves from a “brute-force hunter” into a “sophisticated librarian” organically, without the maintenance overhead of traditional pre-indexed databases.
+
+---
+
+### 3.5 Experimental Validation
+
+The LENS framework’s effectiveness has been validated through rigorous controlled evaluation:
+
+| Setting | LENS (Sirchmunk DEEP) | ReAct Baseline |
+| --- | --- | --- |
+| **500-question controlled eval** | 62.4% EM, 84.8% evidence recall | 65.2% EM, 50.4% evidence recall |
+| **150-question fullwiki** (raw Wikipedia, zero indexing) | 43.3% EM, 84.0% evidence recall | 42.7% EM, 70.7% evidence recall |
+
+These results reveal a key insight: LENS trades a small margin on headline accuracy for dramatically better evidence grounding. In the fullwiki setting — where no indexing or preprocessing is performed — LENS achieves comparable EM while providing 13+ percentage points more evidence recall, validating the source-fidelity claims of the in-context search paradigm.
 
 ---
 
@@ -231,7 +246,8 @@ The era of treating RAG as a static database lookup is ending. By embracing **In
 1. Lewis, P., Perez, E., Piktus, A., et al. (2020). *Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.* NeurIPS 2020. [arXiv:2005.11401](https://arxiv.org/abs/2005.11401)
 2. Guo, Z., Qian, C., et al. (2024). *LightRAG: Simple and Fast Retrieval-Augmented Generation.* [arXiv:2410.05779](https://arxiv.org/abs/2410.05779) | [GitHub](https://github.com/HKUDS/LightRAG)
 3. VectifyAI. (2025). *PageIndex: Extracting and Understanding Financial Reports with LLM.* [GitHub](https://github.com/VectifyAI/PageIndex)
-4. ModelScope. (2025). *Sirchmunk: An Embedding-Free, Agentic Search Engine for Raw Data.* [GitHub](https://github.com/modelscope/sirchmunk)
-5. Yao, S., Zhao, J., Yu, D., et al. (2023). *ReAct: Synergizing Reasoning and Acting in Language Models.* ICLR 2023. [arXiv:2210.03629](https://arxiv.org/abs/2210.03629)
-6. Anthropic. (2024). *Model Context Protocol (MCP) Specification.* [Documentation](https://modelcontextprotocol.io)
-7. Kaddour, J., Harris, J., Mozes, M., et al. (2023). *Challenges and Applications of Large Language Models.* [arXiv:2307.10169](https://arxiv.org/abs/2307.10169)
+4. ModelScope. (2026). *Sirchmunk: An Embedding-Free, Agentic Search Engine for Raw Data.* [GitHub](https://github.com/modelscope/sirchmunk)
+5. Wang, X., et al. (2026). *LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents.* [arXiv:2608.16185](https://arxiv.org/abs/2608.16185)
+6. Yao, S., Zhao, J., Yu, D., et al. (2023). *ReAct: Synergizing Reasoning and Acting in Language Models.* ICLR 2023. [arXiv:2210.03629](https://arxiv.org/abs/2210.03629)
+7. Anthropic. (2024). *Model Context Protocol (MCP) Specification.* [Documentation](https://modelcontextprotocol.io)
+8. Kaddour, J., Harris, J., Mozes, M., et al. (2023). *Challenges and Applications of Large Language Models.* [arXiv:2307.10169](https://arxiv.org/abs/2307.10169)