Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Paper ā¢ 2610.20344 ā¢ Published ā¢ 63
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
YuyaoGeĀ
authored a
paper 13 days ago
YuyaoGeĀ
submitted a
paper to Daily Papers 14 days ago
YuyaoGeĀ
authored 4
papers 19 days ago
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
Paper ā¢ 2610.09832 ā¢ Published ā¢ 18
Kimi K2.5: Visual Agentic Intelligence
Paper ā¢ 2602.02276 ā¢ Published ā¢ 280
Gated Differentiable Working Memory for Long-Context Language Modeling
Paper ā¢ 2601.12906 ā¢ Published
Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
Paper ā¢ 2511.12344 ā¢ Published ā¢ 1
YuyaoGeĀ
submitted a
paper to Daily Papers 21 days ago
Post
104
š¤ We train LLMs ā but how do LLMs reshape AI research itself?
Sharing our new survey, AI4AIR: A Comprehensive Survey on Large Language Models for AI Research š
Rather than treating LLMs as outside helpers for writing or literature review, we map how they enter the ML pipeline itself ā through a 2D taxonomy (research domain Ć pipeline stage) and 5 recurring roles:
š·ļø Annotator Ā· š§Ŗ Synthesizer Ā· āļø Optimizer Ā· š Evaluator Ā· šļø Orchestrator
Our key takeaway: how deeply an LLM can empower a stage is bounded by its validation cost ā which is exactly why data annotation & evaluation are already mature, while model design & full-loop orchestration remain hard.
š Paper (PDF): https://github.com/ICT-FinD-Lab/Awesome-LLMs-for-AI-Research/blob/master/PDF/AI4AIR_Survey_v260601.pdf
š Project: https://ict-find-lab.github.io/Awesome-LLMs-for-AI-Research
ā GitHub: https://github.com/ICT-FinD-Lab/Awesome-LLMs-for-AI-Research
Stars & feedback warmly welcome š
Sharing our new survey, AI4AIR: A Comprehensive Survey on Large Language Models for AI Research š
Rather than treating LLMs as outside helpers for writing or literature review, we map how they enter the ML pipeline itself ā through a 2D taxonomy (research domain Ć pipeline stage) and 5 recurring roles:
š·ļø Annotator Ā· š§Ŗ Synthesizer Ā· āļø Optimizer Ā· š Evaluator Ā· šļø Orchestrator
Our key takeaway: how deeply an LLM can empower a stage is bounded by its validation cost ā which is exactly why data annotation & evaluation are already mature, while model design & full-loop orchestration remain hard.
š Paper (PDF): https://github.com/ICT-FinD-Lab/Awesome-LLMs-for-AI-Research/blob/master/PDF/AI4AIR_Survey_v260601.pdf
š Project: https://ict-find-lab.github.io/Awesome-LLMs-for-AI-Research
ā GitHub: https://github.com/ICT-FinD-Lab/Awesome-LLMs-for-AI-Research
Stars & feedback warmly welcome š
CapitalLiuĀ
submitted a
paper to Daily Papers 5 months ago
ZhenlongYuanĀ
submitted a
paper to Daily Papers 5 months ago
YuyaoGeĀ
updated a
Space 6 months ago
YuyaoGeĀ
published a
Space 6 months ago
YuyaoGeĀ
authored a
paper 8 months ago
YuyaoGeĀ
submitted a
paper to Daily Papers 8 months ago
THEATLASĀ
submitted a
paper to Daily Papers 9 months ago
ShiyuneeĀ
authored a
paper 11 months ago
ShiyuneeĀ
authored 2
papers about 1 year ago
YuyaoGeĀ
authored 2
papers about 1 year ago