127 citations · 168 across the 38 of their papers we have counts for
13 papers · 1 filter
ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments
Shengbin Yue, Hongru Wang, Siyuan Wang +3
Language model agents are increasingly deployed in open-world tool environments, which require balancing exploring unknown capabilities and exploiting known ones. Existing methods…
ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback
Min Zeng, Yuzhou Liu, Zhenyu Cao +5
High-quality tool-use data is critical for training language models to interact effectively with external tools. However, existing synthetic approaches typically follow a generate-…
VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following
Min Zeng, Guanxin Tan, Libin Cen +5
Multimodal instruction-following models require training data that is accurate, diverse, verifiable, and challenging. Existing synthesis pipelines typically follow a one-pass gener…
Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing
Haoyu Wang, Cheng Feng, Liuyang Bian +5
Practical video editing is not only pixel generation: an editor must turn a brief, a clip pool, music metadata, and hard constraints into an executable timeline. We study this deci…
SpatialAfford: Teaching Compact VLMs Where to Look and Where to Ground for Affordance
Yufei Zhang, Chenlu Zhan, Donghui Sun +2
Affordance grounding aims to localize the functional region for interaction, such as the handle to grasp or the button to press, rather than the whole object. This makes it more ch…
REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning
Yunjie Chen, Zihao Chen, Xiaoxin Chen +2
Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool use in large language models…
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance
Kangsheng Duan, Ziyang Xu, Wenyu Liu +3
While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructin…
SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning
Jichao Wang, Liuyang Bian, Yufeng Zhou +9
As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to complex navigation. While Reinforcement Learning (RL) has emerged as a promi…
Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
Hao Wang, Guozhi Wang, Han Xiao +8
Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long hori…
Benchmark Shadows: Data Alignment, Parameter Footprints, and Generalization in Large Language Models
Hongjian Zou, Yidan Wang, Qi Ding +2
Large language models often achieve strong benchmark gains without corresponding improvements in broader capability. We hypothesize that this discrepancy arises from differences in…
Caption First, VQA Second: Knowledge Density, Not Task Format, Drives Multimodal Scaling
Hongjian Zou, Yue Ge, Qi Ding +2
Multimodal large language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less predictable than that of text-on…
UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI Agents
Han Xiao, Guozhi Wang, Hao Wang +7
Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by i…
Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
Yujie Lin, Kunquan Li, Yixuan Liao +2
Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases,…