diff --git a/.github/assets/DeepResearch_Bench.png b/.github/assets/DeepResearch_Bench.png new file mode 100644 index 0000000..324182e Binary files /dev/null and b/.github/assets/DeepResearch_Bench.png differ diff --git a/.github/assets/badge-pypi-dark.svg b/.github/assets/badge-pypi-dark.svg index 31154d8..44372e8 100644 --- a/.github/assets/badge-pypi-dark.svg +++ b/.github/assets/badge-pypi-dark.svg @@ -5,5 +5,5 @@ v0.0.7 + font-size="13" font-weight="700" fill="#ffffff">v0.0.8 \ No newline at end of file diff --git a/.github/assets/badge-pypi-light.svg b/.github/assets/badge-pypi-light.svg index ad30b27..fdeecd7 100644 --- a/.github/assets/badge-pypi-light.svg +++ b/.github/assets/badge-pypi-light.svg @@ -5,5 +5,5 @@ v0.0.7 + font-size="13" font-weight="700" fill="#ffffff">v0.0.8 \ No newline at end of file diff --git a/.github/assets/deepresearch_bench_2.JPG b/.github/assets/deepresearch_bench_2.JPG deleted file mode 100644 index 0f7c846..0000000 Binary files a/.github/assets/deepresearch_bench_2.JPG and /dev/null differ diff --git a/.github/assets/deepresearch_bench_2.png b/.github/assets/deepresearch_bench_2.png new file mode 100644 index 0000000..ca63280 Binary files /dev/null and b/.github/assets/deepresearch_bench_2.png differ diff --git a/EvoScientist/llm/models.py b/EvoScientist/llm/models.py index a7690f4..3d440f0 100644 --- a/EvoScientist/llm/models.py +++ b/EvoScientist/llm/models.py @@ -74,6 +74,7 @@ _MODEL_ENTRIES: list[tuple[str, str, str]] = [ ("gpt-5.3-codex", "gpt-5.3-codex", "custom-openai"), ("gpt-5-mini", "gpt-5-mini", "custom-openai"), # Anthropic (ordered by capability) + ("claude-opus-4-7", "claude-opus-4-7", "anthropic"), ("claude-opus-4-6", "claude-opus-4-6", "anthropic"), ("claude-sonnet-4-6", "claude-sonnet-4-6", "anthropic"), ("claude-opus-4-5", "claude-opus-4-5", "anthropic"), @@ -125,6 +126,7 @@ _MODEL_ENTRIES: list[tuple[str, str, str]] = [ ("kimi-k2.5", "Pro/moonshotai/Kimi-K2.5", "siliconflow"), ("glm-4.7", "Pro/zai-org/GLM-4.7", "siliconflow"), # OpenRouter + ("claude-opus-4.7", "anthropic/claude-opus-4.7", "openrouter"), ("claude-opus-4.6", "anthropic/claude-opus-4.6", "openrouter"), ("claude-sonnet-4.6", "anthropic/claude-sonnet-4.6", "openrouter"), ("gpt-5.4", "openai/gpt-5.4", "openrouter"), @@ -223,7 +225,7 @@ def _apply_auto_config( _is_proxy = False if _is_proxy or (is_third_party and not _supports_thinking): pass - elif model_id.endswith("4-6"): + elif model_id.endswith(("4-6", "4-7")): kwargs["thinking"] = {"type": "adaptive"} kwargs.setdefault("effort", "max") else: diff --git a/README.md b/README.md index 45bb9d5..7d39914 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ - PyPI v0.0.6 + PyPI v0.0.8 @@ -57,7 +57,7 @@ Moving beyond traditional human-in-the-loop systems, EvoScientist adopts a human AI-Generated Best Paper - DeepResearch Bench II #1 + DeepResearch Bench II #1
#1 on DeepResearch Bench II @@ -68,16 +68,21 @@ Moving beyond traditional human-in-the-loop systems, EvoScientist adopts a human - - + -
+ + DeepResearch Bench #1 +
+ #1 on DeepResearch Bench + 		AstaBench Code & Execution #1
#1 on AstaBench Code & Execution 		+ AstaBench Data Analysis #1
#1 on AstaBench Data Analysis +
@@ -117,6 +122,8 @@ Moving beyond traditional human-in-the-loop systems, EvoScientist adopts a human > Looking for ready-to-use research skills? Check out [**EvoSkills**](https://github.com/EvoScientist/EvoSkills) — powered by [**EvoScientist**](https://github.com/EvoScientist/EvoScientist)'s engine and installable skills, the entire end-to-end research lifecycle is covered out of the box. [**EvoSkills**](https://github.com/EvoScientist/EvoSkills) are also compatible with other CLI coding agents. ## 🔥 News +- **[18 Apr 2026]** 🥇 Ranked #1 on [DeepResearch Bench](https://deepresearch-bench.github.io/) at submission time! [**Leaderboard**](https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard) 👈 +- **[13 Apr 2026]** 🥇 Reclaimed #1 on [DeepResearch Bench II](https://agentresearchlab.com/benchmarks/deepresearch-bench-ii/index.html#leaderboard) at submission time! [**Leaderboard**](https://agentresearchlab.com/benchmarks/deepresearch-bench-ii/index.html#leaderboard) 👈 - **[26 Mar 2026]** 🥇 Ranked #1 on [AstaBench Data Analysis](https://allenai-asta-bench-leaderboard.hf.space/home) at submission time! [**Leaderboard**](https://allenai-asta-bench-leaderboard.hf.space/data-analysis) 👈 - **[25 Mar 2026]** 🥇 Ranked #1 on [AstaBench Code & Execution](https://allenai-asta-bench-leaderboard.hf.space/home) at submission time! [**Leaderboard**](https://allenai-asta-bench-leaderboard.hf.space/code-execution) 👈 - **[13 Mar 2026]** 🚀 [**EvoScientist**](https://github.com/EvoScientist/EvoScientist) officially debuts! diff --git a/README.zh-CN.md b/README.zh-CN.md index 966706f..5f89647 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -15,7 +15,7 @@ - PyPI v0.0.6 + PyPI v0.0.8 @@ -64,7 +64,7 @@ EvoScientist 超越了传统的人在回路（Human-in-the-Loop）模式，采 AI 生成最佳论文 - DeepResearch Bench II #1 + DeepResearch Bench II #1
DeepResearch Bench II 第一名 @@ -75,12 +75,17 @@ EvoScientist 超越了传统的人在回路（Human-in-the-Loop）模式，采 - + -
+ + DeepResearch Bench #1 +
+ DeepResearch Bench 第一名 + 		AstaBench Code & Execution #1
AstaBench 代码与执行榜第一名 		+ AstaBench Data Analysis #1
AstaBench 数据分析榜第一名 @@ -126,6 +131,8 @@ EvoScientist 超越了传统的人在回路（Human-in-the-Loop）模式，采 ## 🔥 动态 +- **[2026 年 4 月 18 日]** 🥇 提交时在 [DeepResearch Bench](https://deepresearch-bench.github.io/) 排名第一！[**排行榜**](https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard) 👈 +- **[2026 年 4 月 13 日]** 🥇 再度登顶！提交时在 [DeepResearch Bench II](https://agentresearchlab.com/benchmarks/deepresearch-bench-ii/index.html#leaderboard) 重回第一！[**排行榜**](https://agentresearchlab.com/benchmarks/deepresearch-bench-ii/index.html#leaderboard) 👈 - **[2026 年 3 月 26 日]** 🥇 提交时在 [AstaBench 数据分析](https://allenai-asta-bench-leaderboard.hf.space/home) 排名第一！[**排行榜**](https://allenai-asta-bench-leaderboard.hf.space/data-analysis) 👈 - **[2026 年 3 月 25 日]** 🥇 提交时在 [AstaBench 代码与执行](https://allenai-asta-bench-leaderboard.hf.space/home) 排名第一！[**排行榜**](https://allenai-asta-bench-leaderboard.hf.space/code-execution) 👈 - **[2026 年 3 月 13 日]** 🚀 [**EvoScientist**](https://github.com/EvoScientist/EvoScientist) 正式亮相！ diff --git a/pyproject.toml b/pyproject.toml index 62f2f9a..38bc02d 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "EvoScientist" -version = "0.0.7" +version = "0.0.8" description = "EvoScientist: Towards Self-Evolving AI Scientists for End-to-End Scientific Discovery" readme = "README.md" requires-python = ">=3.11" @@ -16,7 +16,7 @@ classifiers = [ "Programming Language :: Python :: 3", ] dependencies = [ - "deepagents>=0.5.1", + "deepagents>=0.5.3", "langchain>=1.2.12", "langchain-anthropic>=1.4.0", "langchain-openai>=1.1", diff --git a/uv.lock b/uv.lock index 7135a32..eebf5f0 100644 --- a/uv.lock +++ b/uv.lock @@ -794,7 +794,7 @@ wheels = [ [[package]] name = "deepagents" -version = "0.5.1" +version = "0.5.3" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "langchain" }, @@ -804,9 +804,9 @@ dependencies = [ { name = "langsmith" }, { name = "wcmatch" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/ef/69/a28e6cd6dd037a28720ae82ef69eacdf8cf8b5291870ac6760e66796b1ae/deepagents-0.5.1.tar.gz", hash = "sha256:5d2b5e1a50dfbf2af97800725d7ac9850e96bab022365e0c2fc3f6291f279635", size = 110322, upload-time = "2026-04-07T22:58:04.581Z" } +sdist = { url = "https://files.pythonhosted.org/packages/bd/c5/fbf36ff707f7ad4ff2d1590ba8c3b44622370955c74f0c84e4bb1b101d7d/deepagents-0.5.3.tar.gz", hash = "sha256:cbe63bd482c37d3aef883326f5dde70effcd489e67fc91834ffe7a8769796a5f", size = 122654, upload-time = "2026-04-15T13:06:34.875Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/25/97/30b8ca49a72c7bf555732dc33ca623e3883b3e030b1b55f3085d92c6f289/deepagents-0.5.1-py3-none-any.whl", hash = "sha256:714853597feee9b24e7385fa575b72568536dcb263b9e91f3ba5d2fd073967a1", size = 123746, upload-time = "2026-04-07T22:58:03.341Z" }, + { url = "https://files.pythonhosted.org/packages/30/8f/40c91a29e4f094e5a1375e33309a3d0ca2e5204816d1dcdcd41ac38410d8/deepagents-0.5.3-py3-none-any.whl", hash = "sha256:f1f1c968f17a5bfb0a6d588d00c2e83264cdac0faa91f7b522892d5a2bd303cb", size = 138475, upload-time = "2026-04-15T13:06:33.593Z" }, ] [[package]] @@ -873,7 +873,7 @@ wheels = [ [[package]] name = "evoscientist" -version = "0.0.7" +version = "0.0.8" source = { editable = "." } dependencies = [ { name = "deepagents" }, @@ -960,7 +960,7 @@ requires-dist = [ { name = "aiohttp", marker = "extra == 'slack'", specifier = ">=3.9" }, { name = "build", marker = "extra == 'dev'", specifier = ">=1.0" }, { name = "ccproxy-api", marker = "extra == 'oauth'", specifier = ">=0.2.7" }, - { name = "deepagents", specifier = ">=0.5.1" }, + { name = "deepagents", specifier = ">=0.5.3" }, { name = "discord-py", marker = "extra == 'all-channels'", specifier = ">=2.3" }, { name = "discord-py", marker = "extra == 'discord'", specifier = ">=2.3" }, { name = "faster-whisper", marker = "extra == 'stt'", specifier = ">=1.0" },