Knowledge Engineer Group @ Tsinghua University

university

https://keg.cs.tsinghua.edu.cn/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

mozhu submitted a paper 6 days ago

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

mozhu submitted a paper 6 days ago

Aspire: Can Models Self-Evolve from Vague Goals?

mozhu submitted a paper 6 days ago

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

View all activity

Papers

Memory for Large Language Models

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

View all Papers

submitted 3 papers to Daily Papers 6 days ago

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published 9 days ago • 261

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published 10 days ago • 225

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

Paper • 2608.31100 • Published 10 days ago • 38

published a dataset 7 days ago

THU-KEG/SAEVerbalizer-Data

Viewer • Updated 7 days ago • 2.2k • 33

published a model 7 days ago

THU-KEG/SAEVerbalizer-27B

Text Generation • 27B • Updated 7 days ago • 500

updated a model 7 days ago

THU-KEG/SAEVerbalizer-27B

Text Generation • 27B • Updated 7 days ago • 500

updated a dataset 7 days ago

THU-KEG/SAEVerbalizer-Data

Viewer • Updated 7 days ago • 2.2k • 33

submitted a paper to Daily Papers 8 days ago

CogEvol: Towards Efficient and Reliable Learning Environment Generation

Paper • 2608.30968 • Published 10 days ago • 30

submitted a paper to Daily Papers about 1 month ago

Memory for Large Language Models

Paper • 2607.25380 • Published Jul 28 • 16

authored a paper 3 months ago

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

Paper • 2606.13662 • Published Jun 11 • 33

authored a paper 3 months ago

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

Paper • 2606.13662 • Published Jun 11 • 33

submitted a paper to Daily Papers 3 months ago

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

Paper • 2606.13662 • Published Jun 11 • 33

submitted a paper to Daily Papers 3 months ago

Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces

Paper • 2605.29288 • Published May 28 • 9

updated a collection 3 months ago

LongTraceRL

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards • 5 items • Updated Jun 1 • 1

updated 3 models 3 months ago

THU-KEG/LongTraceRL-30B

Reinforcement Learning • 31B • Updated Jun 1 • 6 • 1

THU-KEG/LongTraceRL-8B

Reinforcement Learning • Updated Jun 1 • 1

THU-KEG/LongTraceRL-4B

Reinforcement Learning • 4B • Updated Jun 1 • 7 • 1

updated a dataset 3 months ago

THU-KEG/LongTraceRL

Viewer • Updated Jun 1 • 2.82k • 95 • 2

submitted a paper to Daily Papers 3 months ago

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

Paper • 2605.31584 • Published May 29 • 43

authored a paper 3 months ago

Benchmarking Foundation Models with Language-Model-as-an-Examiner

Paper • 2306.04181 • Published Jun 7, 2023