25 citations · 54 across the 28 of their papers we have counts for
11 papers · 1 filter
Harness Policy Distillation: Aligning Agent Policies with Runtime Semantics
Junze Zhu, Weihao Chen, Zhiyang Zhou +2
Deploying a general-purpose model as an agent means running it inside a product-specific runtime harness that decides which actions are executable, how state advances, and when the…
OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools
Chenyang Yan, Yingying Zhang, Kanzhi Cheng +21
We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes. We make three key advances: (1) Diverse environments with simulated comme…
Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis
Yantao Li, Huanlin Gao, Fang Zhao +12
Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them in parallel. Its lossless g…
MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment
Changhao Xiang, Shangyu Xing, Zhen Wu +2
Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual de…
OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories
Changhao Xiang, Shilin Zhang, Zheng Ma +8
Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capabili…
Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems
Junze Zhu, Weihao Chen, Xuanwang Zhang +2
The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving capabilities, yet the centralized orchestration topology remains a critical po…
Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination
Jinrui Jiang, Zhangtai Wu, Zhen Wu +1
Modality-conflict hallucination occurs when multimodal large language models (MLLMs) prioritize erroneous textual premises over contradictory visual evidence. To understand why vis…
CogGen: A Cognitively Inspired Recursive Framework for Deep Research Report Generation
Kuo Tian, Pengfei Sun, Zhen Wu +2
The autonomous synthesis of deep research reports represents a critical frontier for Large Language Models (LLMs), demanding sophisticated information orchestration and non-linear…
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
Yuhang Wu, Xiangqing Shen, Fanfan Wang +4
Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated…
WebNavigator: Global Web Navigation via Interaction Graph Retrieval
Xuanwang Zhang, Yuteng Han, Jinnan Qi +5
Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this limitation stems…
PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment
Yantao Li, Qiang Hui, Chenyang Yan +8
Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness an…