1 citations · 1 across the 4 of their papers we have counts for
6 papers
TRACE: Trajectory Selection for Parallel Scaling of Search Agents
Qisheng Zhou, Zhen Xiong, Qiaoyu Tan
Parallel search may generate a correct answer that final-answer voting fails to select. We formulate this consolidation stage as trajectory selection and introduce TRACE (Trajector…
EASE: Behavior-Adaptive Skill Curation for Self-Evolving Agents
Zhen Xiong, Qiaoyu Tan
Agent skills provide a lightweight mechanism for self-evolving agents to accumulate reusable procedural knowledge without updating model parameters. However, existing learned skill…
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
Jiaxi Li, Ke Deng, Yun Wang +5
Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks. A growing line of work studies online skill learning, where agents c…
CrystalICL: Enabling In-Context Learning for Crystal Generation
Ruobing Wang, Qiaoyu Tan, Yili Wang +2
Designing crystal materials with desired physicochemical properties remains a fundamental challenge in materials science. While large language models (LLMs) have demonstrated stron…
Concept-Centric Token Interpretation for Vector-Quantized Generative Models
Tianze Yang, Yucheng Shi, Mengnan Du +4
Vector-Quantized Generative Models (VQGMs) have emerged as powerful tools for image generation. However, the key component of VQGMs -- the codebook of discrete tokens -- is still n…
Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
Yucheng Shi, Qiaoyu Tan, Xuansheng Wu +3
Large Language Models (LLMs) have shown proficiency in question-answering tasks but often struggle to integrate real-time knowledge, leading to potentially outdated or inaccurate r…