17 papers
FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis
Kou Shi, Zun Wang, Qisheng Su +10
Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks remains challenging. Each task couples an instruction, an initialize…
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
Zhen Fang, Yu Zeng, Wenxuan Huang +17
We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding couple…
ACC: Compiling Agent Trajectories for Long-Context Training
Qisheng Su, Zhen Fang, Shiting Huang +8
Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heur…
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
Qingnan Ren, Shun Zou, Shiting Huang +11
As autonomous coding agents become capable of handling increasingly long-horizon tasks, they have gradually demonstrated the potential to complete end-to-end software development.…
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
Yiming Zhao, Yu Zeng, Wenxuan Huang +11
Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localiza…
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
Ziao Zhang, Kou Shi, Shiting Huang +13
As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current ben…
Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models
Yu Zeng, Wenxuan Huang, Zhen Fang +14
Multimodal Large Language Models (MLLMs) have advanced VQA and now support Vision-DeepResearch systems that use search engines for complex visual-textual fact-finding. However, eva…
Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
Shiting Huang, Zecheng Li, Yu Zeng +7
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for enhancing the reasoning capabilities of Large Language Models (LLMs). Despite its eff…
VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
Qiuchen Wang, Shihang Wang, Yu Zeng +9
Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) metho…
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
Ruiyan Han, Zhen Fang, XinYu Sun +9
While Unified Multimodal Models (UMMs) have achieved remarkable success in cross-modal comprehension, a significant gap persists in their ability to leverage such internal knowledg…
Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
Wenxuan Huang, Yu Zeng, Qiuchen Wang +14
Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowled…
DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action
Zhen Fang, Zhuoyang Liu, Jiaming Liu +7
To build a generalizable Vision-Language-Action (VLA) model with strong reasoning ability, a common strategy is to first train a specialist VLA on robot demonstrations to acquire r…
Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models
Yu Zeng, Wenxuan Huang, Shiting Huang +9
Although current large Vision-Language Models (VLMs) have advanced in multimodal understanding and reasoning, their fundamental perceptual and reasoning abilities remain limited. S…
CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios
Shiting Huang, Zhen Fang, Zehui Chen +6
The ability of large language models (LLMs) to utilize external tools has enabled them to tackle an increasingly diverse range of tasks. However, as the tasks become more complex a…
VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
Qiuchen Wang, Ruixue Ding, Yu Zeng +6
Effectively retrieving, reasoning and understanding visually rich information remains a challenge for RAG methods. Traditional text-based methods cannot handle visual-related infor…
VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning
Yukun Qi, Yiming Zhao, Yu Zeng +7
The advancement of Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs) and large vision-language models (LVLMs). However, a…
V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction
Yiming Zhao, Yu Zeng, Yukun Qi +8
Large Vision-Language Models (LVLMs) have made significant strides in the field of video understanding in recent times. Nevertheless, existing video benchmarks predominantly rely o…