HKUST - AI4Reasoning Team

university

https://github.com/HKAIR-Lab

AI & ML interests

None defined yet.

Recent Activity

chuxuecao authored a paper 3 days ago

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms

chuxuecao authored a paper 3 days ago

SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent

chuxuecao authored a paper 3 days ago

Authorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Step Tool Use

View all activity

authored 3 papers 3 days ago

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms

Paper • 2605.06716 • Published May 7 • 5

SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent

Paper • 2608.07449 • Published Aug 7 • 1

Authorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Step Tool Use

Paper • 2611.09113 • Published 6 days ago • 8

submitted a paper to Daily Papers 3 days ago

Authorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Step Tool Use

Paper • 2611.09113 • Published 6 days ago • 8

authored a paper 8 months ago

Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training

Paper • 2603.07223 • Published Mar 7 • 13

authored a paper 9 months ago

Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification

Paper • 2601.22642 • Published Jan 30 • 9

submitted a paper to Daily Papers 9 months ago

Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification

Paper • 2601.22642 • Published Jan 30 • 9

authored 2 papers 10 months ago

LRAS: Advanced Legal Reasoning with Agentic Search

Paper • 2601.07296 • Published Jan 12 • 3

MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data

Paper • 2512.13297 • Published Dec 15, 2025

authored a paper about 1 year ago

WoW: Towards a World omniscient World model Through Embodied Interaction

Paper • 2509.22642 • Published Sep 26, 2025 • 15

authored 3 papers over 1 year ago

Measuring Hong Kong Massive Multi-Task Language Understanding

Paper • 2505.02177 • Published May 4, 2025 • 1

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

Paper • 2506.17104 • Published Jun 20, 2025 • 2

SafeLawBench: Towards Safe Alignment of Large Language Models

Paper • 2506.06636 • Published Jun 7, 2025 • 1

updated a model about 2 years ago

HKAIR-Lab/HK-O1aw

Text Generation • Updated Nov 6, 2024 • 23 • 6

updated a dataset about 2 years ago

HKAIR-Lab/HK-O1aw-SFT-16K

Viewer • Updated Nov 1, 2024 • 16k • 106 • 17

updated a dataset about 2 years ago

HKAIR-Lab/HK-O1aw-SFT-16K

Viewer • Updated Nov 1, 2024 • 16k • 106 • 17

updated a Space about 2 years ago

README