107 citations · 142 across the 21 of their papers we have counts for
23 papers
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
Zhenting Qi, Huangyuan Su, Ao Qu +13
How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of d…
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing
Minglai Yang, Xinyan Velocity Yu, Pengyuan Li +22
Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Optical Character Recognition (OC…
BAGEN: Are LLM Agents Budget-Aware?
Yuxiang Lin, Zihan Wang, Mengyang Liu +9
While agents are increasingly spending more resources, today agent cost is mostly measured only after execution. A Budget-Aware Agent (BAGEN) should treat budget as an active contr…
Triaging Threats to Specialized Guardrails
Wenjie Jacky Mo, Xiaofei Wen, Rui Cai +6
Building robust safety guardrails is essential for deploying Large Language Models across diverse real-world applications. However, this goal remains challenging because safety ris…
Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response
Zihan Wang, Xiang Xu, Hongyuan Zha +1
Healthcare mechanisms are inseparable from the strategic provider response they induce: existing healthcare AI benchmarks hold this response fixed and so cannot evaluate mechanisms…
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…
When does Chain-of-Thought Help: A Markovian Perspective
Zihan Wang, Yijun Dong, Qi Lei
Chain-of-Thought (CoT) prompting is a widely used inference-time technique for improving reasoning, yet its gains are uneven across tasks. We analyze when and why CoT helps by mode…
Your Language Model Secretly Contains Personality Subnetworks
Ruimeng Ye, Zihan Wang, Zinan Ling +4
Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopting different personas and behaviors. Ex…
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
Pingyue Zhang, Zihan Huang, Yue Wang +11
Spatial embodied intelligence requires agents to act to acquire information under partial observability. While multimodal foundation models excel at passive perception, their capac…
Artificial Entanglement in the Fine-Tuning of Large Language Models
Min Chen, Zihan Wang, Canyu Chen +3
Large language models (LLMs) can be adapted to new tasks using parameter-efficient fine-tuning (PEFT) methods that modify only a small number of trainable parameters, often through…
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
Kangrui Wang, Pingyue Zhang, Zihan Wang +13
A key challenge in training Vision-Language Model (VLM) agents, compared to Language Model (LLM) agents, lies in the shift from textual states to complex visual observations. This…
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
Licheng Liu, Zihan Wang, Linjie Li +5
Multi-turn problem solving is critical yet challenging for Large Reasoning Models (LRMs) to reflect on their reasoning and revise from feedback. Existing Reinforcement Learning (RL…
EMCompress: Video-LLMs with Endomorphic Multimodal Compression
Zheyu Fan, Jiateng Liu, Yuji Zhang +4
Video-LLMs face a fundamental tension in long-video reasoning: static, sparse frame sampling either dilutes evidence across task-irrelevant segments at significant cost or misses f…
Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models
Ruimeng Ye, Zihan Wang, Yang Xiao +3
Weak-to-Strong generalization (W2SG) is a new trend to elicit the full capabilities of a strong model with supervision from a weak model. While existing W2SG studies focus on simpl…
Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models
Zihan Wang, Rui Pan, Jiarui Yao +7
We propose Chain-of-Experts (CoE), a new Mixture-of-Experts (MoE) architecture that introduces sequential expert communication within each layer. Unlike traditional MoE models, whe…
MindCube: Spatial Mental Modeling from Limited Views
Qineng Wang, Baiqiao Yin, Pingyue Zhang +11
Can Vision-Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form spatial mental models naturally, internal representations of unseen spac…
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
Zihan Wang, Kangrui Wang, Qineng Wang +15
Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback.…
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
ByteDance Seed, :, Jiaze Chen +267
We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 8…
T*: Re-thinking Temporal Search for Long-Form Video Understanding
Jinhui Ye, Zihan Wang, Haosen Sun +9
Efficiently understanding long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding…
Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models
Zihan Wang, Deli Chen, Damai Dai +3
Parameter-efficient fine-tuning (PEFT) is crucial for customizing Large Language Models (LLMs) with constrained resources. Although there have been various PEFT methods for dense-a…
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-AI, Aixin Liu, Bei Feng +154
We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which…
MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Xingyao Wang, Zihan Wang, Jiateng Liu +4
To solve complex tasks, large language models (LLMs) often require multiple rounds of interactions with the user, sometimes assisted by external tools. However, current evaluation…
RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit
Jiongnan Liu, Jiajie Jin, Zihan Wang +3
Although Large Language Models (LLMs) have demonstrated extraordinary capabilities in many domains, they still have a tendency to hallucinate and generate fictitious responses to u…