111 citations · 496 across the 88 of their papers we have counts for
61 papers · 1 filter
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
Shuai Bai, Jiayong Deng, Sicheng Fan +30
Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both…
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
Zihan Qiu, Zekun Wang, Xiao Li +33
We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and additional 51B parameters of n…
Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?
Qingjie Zhang, Xingzhang Ren, Zixuan Chen +6
Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus mixtures or traced specific…
H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference
Hao Yu, Zheng Li, Dayiheng Liu +1
The NVIDIA Blackwell architecture, with native support for the ultra-fine-grained NVFP4 format, opens new opportunities for accelerating large language model (LLM) inference. NVFP4…
BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences
Ru Peng, Haokai Xu, Xijun Gu +11
While data synthesis for large language models (LLMs) is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanities and social sciences (HSS…
HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs
Ru Peng, Tianyu Zhao, Xijun Gu +9
High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. Data synthesis is a viable alternative and succeeds on closed tasks, yet the hum…
WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning
Zixin Chen, Peng Liu, Haobo Li +7
Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages. In an incident report,…
Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
Xinke Tong, Xuanming Zhang, Tianyi Tang +10
Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding numerical precision and mult…
Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention
Xiao Li, Chengruidong Zhang, Hao Luo +15
Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active corr…
Qwen-AgentWorld: Language World Models for General Agents
Yuxin Zuo, Zikai Xiao, Li Sheng +30
A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investigat…
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Xuanming Zhang, Sining Zhoubian, Yuxuan Chen +8
Autoregressive generation in large language models (LLMs) conventionally decodes from the final layer, assuming that deeper representations yield more reliable next-token predictio…
The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates
Shaobo Wang, Guo Chen, Ziyue Wang +5
With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-…
ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning
Xiaoyuan Li, Keqin Bao, Moxin Li +5
Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubr…
Unified Data Selection for LLM Reasoning
Xiaoyuan Li, Yubo Ma, Chengpeng Li +6
Effectively training Large Language Models (LLMs) for complex, long-CoT reasoning is often bottlenecked by the need for massive high-quality reasoning data. Existing methods are ei…
SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs
Xiaoyuan Li, Moxin Li, Keqin Bao +4
Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only b…
SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation
Xiaoyuan Li, Yuzhe Wang, Moxin Li +6
Large Language Models (LLMs) achieve strong performance on standard knowledge evaluation benchmarks, yet recent work shows that their knowledge capabilities remain brittle under qu…
On Predicting the Post-training Potential of Pre-trained LLMs
Xiaoyuan Li, Yubo Ma, Kexin Yang +5
The performance of Large Language Models (LLMs) on downstream tasks is fundamentally constrained by the capabilities acquired during pre-training. However, traditional benchmarks l…
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation
Xiaomeng Hu, Yinger Zhang, Fei Huang +7
AI agents are expected to perform professional work across hundreds of occupational domains (from emergency department triage to nuclear reactor safety monitoring to customs import…
ClinConsensus: A Physician-Calibrated Benchmark for Evaluating Clinical Rubric Coverage in Chinese Medical LLMs
Xiang Zheng, Han Li, Wenjie Luo +15
Open-ended medical LLM evaluation remains weakly grounded in physician-calibrated coverage of clinically relevant response criteria, especially in localized clinical settings. We i…
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Shaobo Wang, Xuan Ouyang, Tianyi Xu +9
As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall, pre-training is shifting from more tokens to better tokens. However, existing methods either…
HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam
Weiqi Zhai, Zhihai Wang, Jinghang Wang +33
Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models on challenging, multi-domain questions. However, community-led analyses…
A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training
Zihan Qiu, Zeyu Huang, Kaiyue Wen +16
We investigate the functional role of emergent outliers in large language models, specifically attention sinks (a few tokens that consistently receive large attention logits) and r…
PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice
Yuzhen Shi, Huanghai Liu, Yiran Hu +27
As large language models (LLMs) are increasingly applied to legal domain-specific tasks, evaluating their ability to perform legal work in real-world settings has become essential.…
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Mingxin Li, Yanzhao Zhang, Dingkun Long +9
In this report, we introduce the Qwen3-VL-Embedding and Qwen3-VL-Reranker model series, the latest extensions of the Qwen family built on the Qwen3-VL foundation model. Together, t…