activity
20242026
collaborators

25 papers

cs.AI2026

DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations

Jiazhen Jiang, Boxi Cao, Lingyong Yan +6

As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating…

cs.AI2026

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

Lingyong Yan, Can Xu, Yukun Zhao +13

Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame problems, acquire evidence, veri…

cs.AI2026

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

Dongsheng Zhu, Xuchen Ma, Yucheng Shen +5

Existing benchmarks evaluate Tool-Integrated Reasoning (TIR) in LLMs on idealized ''happy paths'', largely overlooking real-world tool failures. We introduce ToolMaze, a benchmark…

cs.CV2026

Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis

Jiulong Wu, Yucheng Shen, Lingyong Yan +4

Facial Emotion Analysis (FEA) extends traditional facial emotion recognition by incorporating explainable, fine-grained reasoning. The task integrates three subtasks: emotion recog…

cs.AI2026

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems

Yiqun Chen, Wei Yang, Erhan Zhang +14

LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely op…

cs.CV2026

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)

Guanyi Qin, Jie Liang, Bingbing Zhang +50

In this paper, we present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1: Professional Image Quality Asses…