collaborators

21 papers

cs.CL2026

EASy: Towards Efficient LLM-Based Agentic System

Junnan Liu, Linhao Luo, Thuy-Trang Vu +1

Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing systems primarily optimize task…

cs.MA2026

The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems

Thi-Nhung Nguyen, Linhao Luo, Amardeep Kaur +5

Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups. While prior work has mainly focused on…

cs.CL2026

AIPO: Learning to Reason from Active Interaction

Junnan Liu, Linhao Luo, Thuy-Trang Vu +1

Recent advances in large language models (LLMs) have demonstrated remarkable reasoning capabilities, largely stimulated by Reinforcement Learning with Verifiable Rewards (RLVR). Ho…

cs.AI2026

G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge

Linhao Luo, Zicheng Zhao, Junnan Liu +9

Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge. Retrieval-augmented generation (RAG) mitigates this by inc…

cs.CL2026

GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler

Minghan Wang, Ye Bai, Thuy-Trang Vu +2

Inference-time scaling (ITS) in latent reasoning models typically relies on heuristic perturbations, such as dropout or fixed Gaussian noise, to generate diverse candidate trajecto…

cs.AI2026

LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations

Viet-Thanh Pham, Lizhen Qu, Thuy-Trang Vu +2

Large language models (LLMs) are increasingly deployed as autonomous agents, yet evaluations focus primarily on task success rather than cultural appropriateness or evaluator relia…