@researai/deepscientist 1.5.16 → 1.6.0

package/AISB/image/aisb.b12.embodied_ai.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B12 Embodied AI">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#14213d"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#fca311" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#fca311" opacity="0.12"/>
+  <text x="80" y="120" fill="#fca311" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#f8fafc" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B12 Embodied AI</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #f8fafc; font-size: 32px; line-height: 1.35;">CALVIN task-spec public-dev mini package for headless embodied rollout validation.</div>
+  </foreignObject>
+</svg>

package/AISB/image/aisb.b2.agent_systems.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B2 Agent Systems">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#14213d"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#fca311" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#fca311" opacity="0.12"/>
+  <text x="80" y="120" fill="#fca311" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#f8fafc" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B2 Agent Systems</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #f8fafc; font-size: 32px; line-height: 1.35;">tau2-bench airline public-dev mini package for tool-use task success validation.</div>
+  </foreignObject>
+</svg>

package/AISB/image/aisb.b3.self_evolving_rl.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B3 Self-Evolving Agents">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#14213d"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#fca311" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#fca311" opacity="0.12"/>
+  <text x="80" y="120" fill="#fca311" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#f8fafc" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B3 Self-Evolving Agents</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #f8fafc; font-size: 32px; line-height: 1.35;">SWE-bench Lite public-dev metadata package for self-improvement trajectory validation.</div>
+  </foreignObject>
+</svg>

package/AISB/image/aisb.b4.lm_reasoning.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B4 LM Reasoning">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#14213d"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#fca311" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#fca311" opacity="0.12"/>
+  <text x="80" y="120" fill="#fca311" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#f8fafc" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B4 LM Reasoning</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #f8fafc; font-size: 32px; line-height: 1.35;">MMLU-Pro public-dev reasoning QA package with normalized exact-match scoring.</div>
+  </foreignObject>
+</svg>

package/AISB/image/aisb.b5.math_proof.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B5 Mathematical Proof">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#14213d"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#fca311" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#fca311" opacity="0.12"/>
+  <text x="80" y="120" fill="#fca311" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#f8fafc" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B5 Mathematical Proof</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #f8fafc; font-size: 32px; line-height: 1.35;">FormalMATH-Lite Lean4 theorem-proving package with proof-rate scoring.</div>
+  </foreignObject>
+</svg>

package/AISB/image/aisb.b6.research_process.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B6 Research Process">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#3b1d1d"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#fca5a5" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#fca5a5" opacity="0.12"/>
+  <text x="80" y="120" fill="#fca5a5" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#fff7ed" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B6 Research Process</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #fff7ed; font-size: 32px; line-height: 1.35;">ScienceAgentBench public-input preview package; full upstream references are not redistributable.</div>
+  </foreignObject>
+</svg>

package/AISB/image/aisb.b7.multimodal_fusion.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B7 Multimodal Fusion">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#14213d"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#fca311" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#fca311" opacity="0.12"/>
+  <text x="80" y="120" fill="#fca311" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#f8fafc" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B7 Multimodal Fusion</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #f8fafc; font-size: 32px; line-height: 1.35;">MMMU-Pro image-plus-text public-dev mini package with exact-match style scoring.</div>
+  </foreignObject>
+</svg>

package/AISB/image/aisb.b8.lifesci_drug.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B8 LifeSci Drug Discovery">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#12342f"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#a7f3d0" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#a7f3d0" opacity="0.12"/>
+  <text x="80" y="120" fill="#a7f3d0" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#f8fafc" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B8 LifeSci Drug Discovery</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #f8fafc; font-size: 32px; line-height: 1.35;">ADMET-only public-dev BenchStore pilot using five real TDC molecular-property endpoints.</div>
+  </foreignObject>
+</svg>

package/AISB/image/aisb.b9.material_science.svg

@@ -0,0 +1,16 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-label="AISB B9 Material Science">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#2f2912"/>
+      <stop offset="1" stop-color="#0f172a"/>
+    </linearGradient>
+  </defs>
+  <rect width="1200" height="630" rx="48" fill="url(#g)"/>
+  <circle cx="980" cy="110" r="210" fill="#fde68a" opacity="0.18"/>
+  <circle cx="180" cy="520" r="170" fill="#fde68a" opacity="0.12"/>
+  <text x="80" y="120" fill="#fde68a" font-family="Georgia, serif" font-size="42" font-weight="700">AISB BenchStore Pilot</text>
+  <text x="80" y="250" fill="#f8fafc" font-family="Georgia, serif" font-size="72" font-weight="700">AISB B9 Material Science</text>
+  <foreignObject x="80" y="305" width="900" height="180">
+    <div xmlns="http://www.w3.org/1999/xhtml" style="font-family: Verdana, sans-serif; color: #f8fafc; font-size: 32px; line-height: 1.35;">Matbench Discovery WBM mini package for crystal-stability prediction validation.</div>
+  </foreignObject>
+</svg>

package/README.md

@@ -1,15 +1,9 @@
-<h1 align="center">
-  <img src="assets/branding/logo.svg" alt="DeepScientist logo" width="92" />
+<h1 align="center" style="font-size: 3.25rem; line-height: 1.02; margin-bottom: 0.4rem;">
+  <img src="assets/branding/logo.svg" alt="DeepScientist logo" width="50" />
   DeepScientist
 </h1>
 
 
-<p align="center">
-  DeepScientist is a local-first AI research studio, Bring your own AI scientist onto your machine in 15 minutes.
-</p>
-
-
-
 <p align="center">
   <a href="https://github.com/ResearAI/DeepScientist">GitHub</a> |
   <a href="README_ZH.md">中文文档</a> |
@@ -20,10 +14,13 @@
 
 <p align="center">
   <a href="https://github.com/ResearAI/DeepScientist"><img alt="GitHub stars" src="https://img.shields.io/github/stars/ResearAI/DeepScientist?style=for-the-badge&logo=github"></a>
-  <a href="https://openreview.net/forum?id=cZFgsLq8Gs"><img alt="ICLR 2026" src="https://img.shields.io/badge/ICLR-2026-blue?style=for-the-badge&logo=openreview"></a>
+  <a href="https://event.baai.ac.cn/activities/962"><img alt="Watch Video" src="https://img.shields.io/badge/Watch-Video-5B7266?style=for-the-badge"></a>
   <a href="LICENSE"><img alt="License Apache-2.0" src="https://img.shields.io/badge/License-Apache%202.0-yellow.svg?style=for-the-badge"></a>
   <a href="https://www.python.org/"><img alt="Python 3.11+" src="https://img.shields.io/badge/Python-3.11%2B-blue?style=for-the-badge&logo=python&logoColor=white"></a>
-  <a href="https://www.npmjs.com/package/@researai/deepscientist"><img alt="npm @researai/deepscientist" src="https://img.shields.io/badge/npm-%40researai%2Fdeepscientist-CB3837?style=for-the-badge&logo=npm&logoColor=white"></a>
+</p>
+
+<p align="center">
+  <a href="https://openreview.net/forum?id=cZFgsLq8Gs"><img alt="ICLR 2026 Top 10 Badge" src="assets/readme/iclr2026_top10_badge.svg" height="44"></a>
 </p>
 
 <p align="center">
@@ -33,16 +30,29 @@
   <strong>Human takeover anytime</strong>
 </p>
 
+<p align="center">
+  <strong>Built-in runners: Codex, Claude Code, Kimi Code, OpenCode</strong>
+</p>
+
 <p align="center">
   <a href="docs/en/00_QUICK_START.md">Quick Start</a> •
   <a href="docs/en/02_START_RESEARCH_GUIDE.md">Launch Your First Project</a> •
   <a href="docs/en/12_GUIDED_WORKFLOW_TOUR.md">Product Tour</a> •
-  <a href="docs/en/15_CODEX_PROVIDER_SETUP.md">Model Setup</a>
+  <a href="docs/en/15_CODEX_PROVIDER_SETUP.md">Codex Setup</a> •
+  <a href="docs/en/24_CLAUDE_CODE_PROVIDER_SETUP.md">Claude Setup</a> •
+  <a href="docs/en/27_KIMI_CODE_PROVIDER_SETUP.md">Kimi Setup</a> •
+  <a href="docs/en/25_OPENCODE_PROVIDER_SETUP.md">OpenCode Setup</a>
+</p>
+
+<p align="center">
+  Maintainers: <a href="docs/en/22_BENCHSTORE_YAML_REFERENCE.md">BenchStore YAML Guide</a>
 </p>
 
 ![deepscientist_install](https://github.com/user-attachments/assets/d8244944-4f70-4e08-94e3-002b74ce70fb)
 
-If you are tired of paper overload, broken baselines, scattered experiment logs, and late-night writing cleanup, give the project a star first, then keep scrolling to see how much research grunt work it can take off your plate.
+Unlike one-shot **AI Scientist** or **autoresearch-style systems**, DeepScientist is a **local-first autonomous research studio** that keeps the full loop moving on your machine, from **baselines** and **experiment rounds** to **paper-ready outputs**, with a **10-minute setup**. Powered by **Findings Memory**, **Bayesian optimization**, and the **Research Map**, it keeps turning each new result into the next starting point and goes deep through broader exploration and, when needed, **thousands of experiment validations**.
+
+If you want the technical deep dive behind DeepScientist, watch the [Video](https://event.baai.ac.cn/activities/962).
 
 ---
 
@@ -244,25 +254,103 @@ We believe a system that is actually suitable for research should at least satis
 
 If that sounds like the way you want to work, DeepScientist is worth trying now.
 
-## Get Started In 30 Seconds
+## 🚀 Get Started In 30 Seconds
 
-If you want to try it right now, the shortest path is:
+If you want to try it right now, choose one of these two paths: run the npm commands yourself, or ask the coding tool you already use to install it for you.
 
 Platform note: DeepScientist fully supports Linux and macOS. Native Windows support is currently experimental (strongly recommend WSL2).
 
+### Option 1: Manual Install With npm
+
+Use this path when you already know which runner you want and prefer to control the install, login, and launch commands yourself.
+
+DeepScientist ships four built-in runners:
+
+- `codex`: use this when `codex` already works directly on your machine
+- `claude`: use this when `claude` already works directly on your machine
+- `kimi`: use this when `kimi` already works directly on your machine
+- `opencode`: use this when `opencode` already works directly on your machine
+
+If one of these CLIs already works for you, DeepScientist can usually meet you there instead of asking you to rebuild your whole setup first.
+
+Think of the startup choice like this: bring one runner that already works, and DeepScientist gives you a persistent local research workspace around it.
+
+If you just want the safest recommendation, start with Codex first.
+
+🎯 Recommended first run: `codex`
+
 ```bash
 npm install -g @researai/deepscientist
-codex --login
+codex login
 ds --here
 ```
 
+If Claude Code already works directly in your shell, use this lane:
+
+```bash
+npm install -g @researai/deepscientist
+claude --version
+ds doctor --runner claude
+ds --here --runner claude
+```
+
+If Kimi Code already works directly in your shell, use this lane:
+
+```bash
+npm install -g @researai/deepscientist
+kimi --version
+ds doctor --runner kimi
+ds --here --runner kimi
+```
+
+If OpenCode already works directly in your shell, use this lane:
+
+```bash
+npm install -g @researai/deepscientist
+opencode --version
+ds doctor --runner opencode
+ds --here --runner opencode
+```
+
+If you want to connect Gemini or Ollama, first use the runner-specific docs instead of guessing DeepScientist fields:
+
+- Gemini: prefer [OpenCode Setup](docs/en/25_OPENCODE_PROVIDER_SETUP.md)
+- Ollama: choose Codex, Claude Code, or OpenCode with [Local Model Backends Guide](docs/en/21_LOCAL_MODEL_BACKENDS_GUIDE.md)
+
 To stop the managed local daemon and all currently running agents:
 
 ```bash
 ds --stop
 ```
 
-If `codex --login` is unavailable, run this once first:
+🛠 Prefer installing from a Git checkout instead of npm? Use the repo path directly:
+
+```bash
+git clone https://github.com/ResearAI/DeepScientist.git
+cd DeepScientist
+bash install.sh
+ds
+```
+
+### Option 2: Let A Coding Tool Install It
+
+Use this path when you already work inside Codex, Claude Code, OpenCode, Cursor, or another coding agent. There are only two steps:
+
+1. Launch the coding tool in a directory where you are comfortable installing DeepScientist.
+2. Copy and send this prompt:
+
+```text
+Please install and launch DeepScientist on this machine. The official repo is https://github.com/ResearAI/DeepScientist and the docs start at https://github.com/ResearAI/DeepScientist/blob/main/docs/en/README.md . First inspect Node.js/npm, git, Python, OS, and shell environment. If global npm install is appropriate, run npm install -g @researai/deepscientist and verify ds --help. If source install is safer, git clone https://github.com/ResearAI/DeepScientist.git, cd DeepScientist, read the README, and run bash install.sh. After installation, confirm at least one runner works locally, such as codex, claude, opencode, or kimi; authenticate that CLI first, then run ds doctor --runner <name>, start with ds --here, and report the local URL plus the exact config docs I should read next.
+```
+
+If you plan to edit the UI or TUI from source, also install the workspace dependencies:
+
+```bash
+npm --prefix src/ui install
+npm --prefix src/tui install
+```
+
+If you prefer the interactive first-run flow, run this once first:
 
 ```bash
 codex
@@ -273,10 +361,16 @@ If `codex` still appears to be missing after installing DeepScientist, take the
 ```bash
 npm install -g @openai/codex
 which codex
-codex --login
+codex login
 ```
 
-If `which codex` still prints nothing after that, fix the npm global bin path first, then retry `codex --login` and `ds doctor`.
+If `which codex` still prints nothing after that, fix the npm global bin path first, then retry `codex login` and `ds doctor`.
+
+Important runner note:
+
+- DeepScientist can fall back to npm-bundled helper copies for `codex`, `claude`, and `opencode` when they are installed with the package. Kimi Code is treated as an external CLI unless a compatible local `kimi` helper is present.
+- Runner authentication and provider configuration still belong to the underlying CLI. Make `codex`, `claude`, `kimi`, or `opencode` work once in your shell, then run `ds doctor --runner <name>`.
+- You can also start DeepScientist first with the default runner and switch/configure Claude Code, Kimi Code, or OpenCode later from the web workspace settings.
 
 After startup, the default local address is:
 
@@ -300,34 +394,42 @@ If this is your first run, prefer an isolated environment, a non-root user, and
 
 - [00 Quick Start](docs/en/00_QUICK_START.md)
 - [15 Codex Provider Setup](docs/en/15_CODEX_PROVIDER_SETUP.md)
+- [24 Claude Code Setup](docs/en/24_CLAUDE_CODE_PROVIDER_SETUP.md)
+- [27 Kimi Code Setup](docs/en/27_KIMI_CODE_PROVIDER_SETUP.md)
+- [25 OpenCode Setup](docs/en/25_OPENCODE_PROVIDER_SETUP.md)
 - [09 Doctor](docs/en/09_DOCTOR.md)
 
-## Choose Your Starting Path
+## 🧭 Choose Your Starting Path
 
-### I just want to get it running first
+### ⚡ I just want to get it running first
 
 - [00 Quick Start](docs/en/00_QUICK_START.md)
 - [12 Guided Workflow Tour](docs/en/12_GUIDED_WORKFLOW_TOUR.md)
 
-### I want to launch a real project today
+### 🧪 I want to launch a real project today
 
 - [02 Start Research Guide](docs/en/02_START_RESEARCH_GUIDE.md)
 - [01 Settings Reference](docs/en/01_SETTINGS_REFERENCE.md)
 
-### I mainly work on servers and terminals
+### 🖥 I mainly work on servers and terminals
 
 - [05 TUI Guide](docs/en/05_TUI_GUIDE.md)
+  Includes `ds --tui --debug`, redacted debug JSONL, and Web/TUI comparison guidance.
 
-### I want to connect my own models or external collaboration channels
+### 🔌 I want to connect my own models or external collaboration channels
 
 - [15 Codex Provider Setup](docs/en/15_CODEX_PROVIDER_SETUP.md)
+- [24 Claude Code Setup](docs/en/24_CLAUDE_CODE_PROVIDER_SETUP.md)
+- [27 Kimi Code Setup](docs/en/27_KIMI_CODE_PROVIDER_SETUP.md)
+- [25 OpenCode Setup](docs/en/25_OPENCODE_PROVIDER_SETUP.md)
+- [21 Local Model Backends Guide](docs/en/21_LOCAL_MODEL_BACKENDS_GUIDE.md)
 - [Weixin Connector Guide](docs/en/10_WEIXIN_CONNECTOR_GUIDE.md)
 - [QQ Connector Guide](docs/en/03_QQ_CONNECTOR_GUIDE.md)
 - [Telegram Connector Guide](docs/en/16_TELEGRAM_CONNECTOR_GUIDE.md)
 - [WhatsApp Connector Guide](docs/en/17_WHATSAPP_CONNECTOR_GUIDE.md)
 - [Feishu Connector Guide](docs/en/18_FEISHU_CONNECTOR_GUIDE.md)
 
-### I want to understand the system design first
+### 🧠 I want to understand the system design first
 
 - [Docs Index](docs/en/README.md)
 - [Core Architecture Guide](docs/en/13_CORE_ARCHITECTURE_GUIDE.md)
@@ -376,11 +478,30 @@ If you are developing or maintaining DeepScientist, continue with:
 
 - [Architecture](docs/en/90_ARCHITECTURE.md)
 - [Development Guide](docs/en/91_DEVELOPMENT.md)
+- [BenchStore YAML Guide](docs/en/22_BENCHSTORE_YAML_REFERENCE.md)
 - [CONTRIBUTING](CONTRIBUTING.md)
 
 ## Citation
 
-If DeepScientist helps your research or engineering work, please cite:
+If DeepScientist materially helps your paper, report, or research workflow, please cite the DeepScientist paper and disclose meaningful AI assistance honestly.
+
+This is a strong request for fair academic attribution, not an extra software license condition.
+
+Useful links:
+
+- Paper: `https://openreview.net/forum?id=cZFgsLq8Gs`
+- Repository citation metadata: [CITATION.cff](CITATION.cff)
+- Citation and attribution guidance: [docs/en/26_CITATION_AND_ATTRIBUTION.md](docs/en/26_CITATION_AND_ATTRIBUTION.md)
+- Acknowledgements, including optional FermiLink science-workflow attribution: [docs/en/99_ACKNOWLEDGEMENTS.md](docs/en/99_ACKNOWLEDGEMENTS.md)
+- Name and logo usage: [TRADEMARK.md](TRADEMARK.md)
+
+Suggested acknowledgment text:
+
+```text
+We used DeepScientist to assist parts of the research workflow, including selected planning, implementation, experiment orchestration, analysis, and/or writing support. Final judgments, claims, and reported real experimental results remain the responsibility of the human authors.
+```
+
+DeepScientist is jointly developed by Yixuan Weng, Weixu Zhao, Shichen Li, Zhen Lin, and Minjun Zhu.
 
 ```bibtex
 @inproceedings{
@@ -400,16 +521,59 @@ If this feels like the research workflow you have been waiting for, give the pro
 Welcome to join the WeChat group for discussion.
 
 <p align="center">
-  <img src="assets/readme/wechat.jpg" alt="DeepScientist WeChat group" width="360" />
+  <img src="assets/readme/wechat10.jpg" alt="DeepScientist WeChat group" width="360" />
 </p>
 
 ## More From ResearAI
 
 If you like DeepScientist, you may also want to explore the rest of the ResearAI ecosystem:
 
-| Project | What it does |
-|---|---|
-| [AutoFigure](https://github.com/ResearAI/AutoFigure) | generate publication-ready figures |
-| [AutoFigure-Edit](https://github.com/ResearAI/AutoFigure-Edit) | generate editable vector paper figures |
-| [DeepReviewer-v2](https://github.com/ResearAI/DeepReviewer-v2) | review papers and suggest revisions |
-| [Awesome-AI-Scientist](https://github.com/ResearAI/Awesome-AI-Scientist) | curated AI scientist landscape |
+| Project | What it does | Stars |
+|---|---|---|
+| **[MeOS](https://github.com/ResearAI/MeOS)** | Fork yourself as a Skill, so agents understand you better | ![GitHub stars](https://img.shields.io/github/stars/ResearAI/MeOS?style=flat&logo=github) |
+| [AutoFigure](https://github.com/ResearAI/AutoFigure) | generate publication-ready figures | ![GitHub stars](https://img.shields.io/github/stars/ResearAI/AutoFigure?style=flat&logo=github) |
+| [AutoFigure-Edit](https://github.com/ResearAI/AutoFigure-Edit) | generate editable vector paper figures | ![GitHub stars](https://img.shields.io/github/stars/ResearAI/AutoFigure-Edit?style=flat&logo=github) |
+| [DeepReviewer-v2](https://github.com/ResearAI/DeepReviewer-v2) | review papers and suggest revisions | ![GitHub stars](https://img.shields.io/github/stars/ResearAI/DeepReviewer-v2?style=flat&logo=github) |
+| [Awesome-AI-Scientist](https://github.com/ResearAI/Awesome-AI-Scientist) | curated AI scientist landscape | ![GitHub stars](https://img.shields.io/github/stars/ResearAI/Awesome-AI-Scientist?style=flat&logo=github) |
+
+## Roadmap
+
+We are building DeepScientist as a long-term local-first research operating system.
+
+The next major upgrades focus on four directions:
+
+### 1. Deeper Research Loops
+
+- AI Scientist Benchmark support for more realistic evaluation and comparison
+- smoother automatic baseline upload, download, and reuse
+- stronger experiment replay, comparison, and paper-facing outputs
+
+### 2. Stronger Long-Horizon Memory
+
+- stronger Memory and Findings Memory mechanisms
+- better cross-run and cross-quest reuse
+- less repeated failure and less rediscovery cost over long projects
+
+### 3. Richer Multimodal And Collaborative Workflows
+
+- VideoAnything-style multimodal research capabilities
+- better local-model, connector, and copilot/autonomous collaboration flows
+- a more efficient and more reliable DeepScientist system across local, collaborative, and long-horizon research settings
+
+### 4. Stronger Security And Safer Deployment
+
+- safer local-first and server-side deployment defaults
+- stronger auth, permission, and connector-surface protection
+- less fabrication, lower hallucination, and more verification-grounded outputs
+- better auditability for long-running autonomous research workflows
+
+If this direction is interesting to you, please give the project a `Watch` and a `Star`:
+
+[![Watch DeepScientist](https://img.shields.io/github/watchers/ResearAI/DeepScientist?style=for-the-badge&logo=github&label=Watch%20DeepScientist)](https://github.com/ResearAI/DeepScientist/watchers)
+[![Star DeepScientist](https://img.shields.io/github/stars/ResearAI/DeepScientist?style=for-the-badge&logo=github&label=Star%20DeepScientist)](https://github.com/ResearAI/DeepScientist/stargazers)
+
+---
+
+This project is maintained by WestlakeNLP. If you run into problems, please ask on [DeepWiki](https://deepwiki.com/ResearAI/DeepScientist) first; if it still cannot be resolved, open an issue.
+
+WestlakeNLP is led by ACL Fellow Professor Yue Zhang. If you are interested in a long-term internship, PhD position, or research assistant opportunity, contact Professor Yue Zhang at `zhangyue@westlake.edu.cn`.