HKUST NLP Group

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

lockon authored a paper about 6 hours ago

AgentBaton: Efficient Model Collaboration in Agentic Tasks

lockon authored a paper about 6 hours ago

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

lockon authored a paper about 6 hours ago

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

View all activity

Papers

ProgAgent: Learning Tool Orchestration through Programmatic Training

STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

View all Papers

authored 3 papers about 6 hours ago

AgentBaton: Efficient Model Collaboration in Agentic Tasks

Paper • 2610.35959 • Published 16 days ago • 9

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published Feb 11, 2025 • 51

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Paper • 2510.25726 • Published Oct 29, 2025 • 48

submitted a paper to Daily Papers about 12 hours ago

AgentBaton: Efficient Model Collaboration in Agentic Tasks

Paper • 2610.35959 • Published 16 days ago • 9

authored a paper 20 days ago

ProgAgent: Learning Tool Orchestration through Programmatic Training

Paper • 2610.14774 • Published about 1 month ago • 12

submitted a paper to Daily Papers 25 days ago

ProgAgent: Learning Tool Orchestration through Programmatic Training

Paper • 2610.14774 • Published about 1 month ago • 12

authored 2 papers about 2 months ago

DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale

Paper • 2609.22978 • Published Sep 19 • 5

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published Sep 17 • 205

authored a paper 2 months ago

Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published Feb 28 • 61

updated a dataset 2 months ago

hkust-nlp/Toolathlon

Benchmark • Updated Aug 31 • 1.36k • 7

published a dataset 2 months ago

hkust-nlp/Toolathlon

Benchmark • Updated Aug 31 • 1.36k • 7

updated a dataset 3 months ago

hkust-nlp/Toolathlon-Verified_Trajectories

Updated Aug 6 • 595 • 7

authored a paper 3 months ago

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 49

published a dataset 4 months ago

hkust-nlp/Toolathlon-Verified_Trajectories

Updated Aug 6 • 595 • 7

authored 2 papers 4 months ago

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?

Paper • 2603.00718 • Published Feb 28 • 2

Internalizing World Models via Self-Play Finetuning for Agentic RL

Paper • 2510.15047 • Published Oct 16, 2025

submitted a paper to Daily Papers 6 months ago

STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

Paper • 2605.06527 • Published May 7 • 48

authored 2 papers 6 months ago

SWE-RM: Execution-free Feedback For Software Engineering Agents

Paper • 2512.21919 • Published Dec 26, 2025 • 10

MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era

Paper • 2601.07526 • Published Jan 12 • 23

submitted a paper to Daily Papers 8 months ago

Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published Feb 28 • 61