1 citations · 1 across the 12 of their papers we have counts for
13 papers
ProgAgent: Learning Tool Orchestration through Programmatic Training
Hao Li, Keqing He, Longtao Zheng +4
Large language models (LLMs) are increasingly expected to orchestrate diverse tools over long-horizon tasks. Existing agents typically use Direct Tool Calling (DTC), where the mode…
EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent
Junlong Li, Junxi Li, Yuxiang Yang +3
Most daily activities are inherently procedural. However, existing evaluations for egocentric video understanding seldom address procedural understanding and largely overlook compl…
GUI-C: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning
Junlong Li, Chao Hao, Lap-Pui Chau +1
Existing agentic reinforcement learning methods for GUI grounding have limitations at two levels. At the data level, current approaches typically treat all training samples equally…
Adam's Law: Textual Frequency Law on Large Language Models
Hongyuan Adam Lu, Z. L., Victor Wei +5
While textual frequency has been validated as relevant to human cognition in reading speed, its relatedness to Large Language Models (LLMs) is seldom studied. We propose a novel re…
SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?
Shiqi Chen, Jingze Gai, Ruochen Zhou +13
Real-world tool-using agents operate over long-horizon workflows with recurring structure and diverse demands, where effective behavior requires not only invoking atomic tools but…
Gender Bias in MT for a Genderless Language: New Benchmarks for Basque
Amaia Murillo, Olatz-Perez-de-Viñaspre, Naiara Perez
Large language models (LLMs) and machine translation (MT) systems are increasingly used in our daily lives, but their outputs can reproduce gender bias present in the training data…
The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
Junlong Li, Wenshuo Zhao, Jian Zhao +18
Real-world language agents must handle complex, multi-step workflows across diverse Apps. For instance, an agent may manage emails by coordinating with calendars and file systems,…
Diving into Self-Evolving Training for Multimodal Reasoning
Wei Liu, Junlong Li, Xiwen Zhang +3
Self-evolving trainin--where models iteratively learn from their own outputs--has emerged as a key approach for complex reasoning tasks, addressing the scarcity of high-quality cha…
Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
Fan Zhou, Zengzhi Wang, Qian Liu +2
Large language model pre-training has traditionally relied on human experts to craft heuristics for improving the corpora quality, resulting in numerous rules developed to date. Ho…
Dissecting Human and LLM Preferences
Junlong Li, Fan Zhou, Shichao Sun +3
As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluatio…
Reformatted Alignment
Run-Ze Fan, Xuefeng Li, Haoyang Zou +5
The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone t…
Extending LLMs' Context Window with 100 Samples
Yikai Zhang, Junlong Li, Pengfei Liu
Large Language Models (LLMs) are known to have limited extrapolation ability beyond their pre-trained context window, constraining their application in downstream tasks with length…
The Critique of Critique
Shichao Sun, Junlong Li, Weizhe Yuan +3
Critique, as a natural language description for assessing the quality of model-generated content, has played a vital role in the training, evaluation, and refinement of LLMs. Howev…