-
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
Paper • 2610.28578 • Published • 66 -
InternScience/Sage-A1.5
Text Generation • 36B • Updated • 396 • 195 -
InternScience/Sage-A1.5-FP8
Text Generation • 36B • Updated • 116 • 9 -
InternScience/Sage-A1.5-Q4_K_M-GGUF
Text Generation • 36B • Updated • 5.51k • 38
AI & ML interests
None defined yet.
Recent Activity
Papers
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
InternAgent aims to facilitate AI+X innovative research across diverse scientific domains
-
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
Paper • 2602.08990 • Published • 70 -
BoZhang/OmniCaptioner
8B • Updated • 88 • 20 -
InternScience/StructTable-base
Image-to-Text • 0.3B • Updated • 106 • 13 -
InternScience/MME-Reasoning
Preview • Updated • 282 • 12
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
-
SGI-Bench Leaderboard
🥇10Scientific General Intelligence of LLMs/vLLMs
-
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Paper • 2512.16969 • Published • 122 -
InternScience/SGI-DeepResearch
Viewer • Updated • 318 • 124 • 11 -
InternScience/SGI-IdeaGeneration
Viewer • Updated • 315 • 94 • 4
Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon.
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Paper • 2606.30616 • Published • 104 -
InternScience/Agents-A1
Text Generation • 35B • Updated • 13k • 658 -
InternScience/Agents-A1-FP8
Text Generation • 35B • Updated • 467 • 24 -
InternScience/Agents-A1-Q4_K_M-GGUF
Text Generation • 35B • Updated • 22.3k • 151
ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
-
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
Paper • 2606.07591 • Published • 106 -
InternScience/ResearchClawBench
Benchmark • Updated • 57 • 33.3k • 16 -
ResearchHarness
🚀7Lightweight harness for tool-using LLM agents.
-
ResearchClawBench Task Submission
📦1Validate and submit a ResearchClawBench task ZIP to Hugging Face
-
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
Paper • 2610.28578 • Published • 66 -
InternScience/Sage-A1.5
Text Generation • 36B • Updated • 396 • 195 -
InternScience/Sage-A1.5-FP8
Text Generation • 36B • Updated • 116 • 9 -
InternScience/Sage-A1.5-Q4_K_M-GGUF
Text Generation • 36B • Updated • 5.51k • 38
Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon.
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Paper • 2606.30616 • Published • 104 -
InternScience/Agents-A1
Text Generation • 35B • Updated • 13k • 658 -
InternScience/Agents-A1-FP8
Text Generation • 35B • Updated • 467 • 24 -
InternScience/Agents-A1-Q4_K_M-GGUF
Text Generation • 35B • Updated • 22.3k • 151
InternAgent aims to facilitate AI+X innovative research across diverse scientific domains
-
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
Paper • 2602.08990 • Published • 70 -
BoZhang/OmniCaptioner
8B • Updated • 88 • 20 -
InternScience/StructTable-base
Image-to-Text • 0.3B • Updated • 106 • 13 -
InternScience/MME-Reasoning
Preview • Updated • 282 • 12
ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
-
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
Paper • 2606.07591 • Published • 106 -
InternScience/ResearchClawBench
Benchmark • Updated • 57 • 33.3k • 16 -
ResearchHarness
🚀7Lightweight harness for tool-using LLM agents.
-
ResearchClawBench Task Submission
📦1Validate and submit a ResearchClawBench task ZIP to Hugging Face
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
-
SGI-Bench Leaderboard
🥇10Scientific General Intelligence of LLMs/vLLMs
-
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Paper • 2512.16969 • Published • 122 -
InternScience/SGI-DeepResearch
Viewer • Updated • 318 • 124 • 11 -
InternScience/SGI-IdeaGeneration
Viewer • Updated • 315 • 94 • 4