Papers by Wenyuan Zhang
SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems (2026.acl-long)
Copied to clipboard
Yuzhe Zhang, Feiran Liu, Yi Shan, Xinyi Huang, Xin Yang, Yueqi Zhu, Xuxin Cheng, Cao Liu, Ke Zeng, Terry Jingchen Zhang, Wenyuan Jiang
| Challenge: | Existing benchmarks conflate coordination ability with role-based priors. |
| Approach: | They propose a role-free benchmark for evaluating free-form collaboration under information silos. |
| Outcome: | The proposed benchmark systematically probes coordination capabilities under information silos using 54 configurations and 3 frontier LLMs. |
Don’t Half-listen: Capturing Key-part Information in Continual Instruction Tuning (2025.acl-long)
Copied to clipboard
Yongquan He, Wenyuan Zhang, Xuancheng Huang, Peng Zhang, Lingxun Meng, Xiang Zhou, Ke Zeng, Xunliang Cai
| Challenge: | Existing methods to improve instruction tuning for large language models may cause catastrophic forgetting (CF) CF is a problem where previously learned abilities are degraded . |
| Approach: | They propose a continual instruction tuning method that uses key-part information gain to replay data and refine training objective. |
| Outcome: | The proposed method achieves superior performance on both seen and held-out tasks. |
Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models (2025.naacl-long)
Copied to clipboard
Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang
| Challenge: | Multimodal Large Language Models have shown significant promise in various applications, but a comprehensive evaluation of their long-context capabilities remains underexplored. |
| Approach: | They propose a benchmark to assess the long-context capabilities of multimodal large language models. |
| Outcome: | The proposed benchmark compared MLLMs with API-based and open-source models in a long-context scenario. |
PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf (2026.acl-demo)
Copied to clipboard
Jiarui Liu, Terry Jingchen Zhang, Ryan Faulkner, Xuanqiang Angelo Huang, Vilém Zouhar, Dominik Glandorf, Isabel Dahlgren, Rishit Dagli, Yuen Chen, Felix Leeb, Van Q. Truong, Punya Syon Pandey, Yves Bicker, Suvajit Majumder, Wenyuan Jiang, Zeju Qiu, Sankalan Pal Chowdhury, Mrinmaya Sachan, Bernhard Schölkopf, Mona T. Diab, Zhijing Jin
| Challenge: | Emerging AI-powered writing assistants focus on grammar fixes or simulating peer review with final scores, yet they fall short of providing concrete, actionable suggestions that help students improve their papers during drafting. |
| Approach: | They propose a human-centered writing assistant system that delivers actionable suggestions as Overleaf-native inline comments while leaving the actual writing entirely to human authors. |
| Outcome: | The proposed system outperforms a baseline with the skill library and provides actionable suggestions while leaving the actual writing to human authors. |
Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on large language models (LLMs) fail to detect character knowledge errors, leading to low-quality automatic corpus construction. |
| Approach: | They propose to use a large language model to detect known knowledge errors and an agent-based reasoning method to improve error detection. |
| Outcome: | The proposed method improves the ability of LLMs to detect errors in known knowledge errors and unknown knowledge errors while playing roles. |
A Boundary Offset Prediction Network for Named Entity Recognition (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a fundamental task in natural language processing . span-based methods assign entity types to text spans, resulting in imbalanced sample space . |
| Approach: | They propose a method that predicts boundary offsets between candidate and nearest spans . the method integrates entity type and span representations to generate type-aware boundary offset . |
| Outcome: | The proposed method outperforms existing methods on eight widely-used NER datasets. |
SOTOPIA-: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies on the social simulation of large language model intelligent agents have shown that even expert agents 1 perform significantly worse on challenging social tasks compared to expert agents. |
| Approach: | They propose a framework that dynamically injects a variety of social strategies into expert agents, thereby automating the construction of high-quality social dialogue training corpus. |
| Outcome: | The proposed framework enables the integration of social strategies into language agents and improves their performance on social tasks. |
AttnPO: Attention-Guided Process Supervision for Efficient Reasoning (2026.acl-long)
Copied to clipboard
Shuaiyi Nie, null Dingsiyu, Wenyuan Zhang, Linhao Yu, Tianmeng Yang, Yao Chen, Weichong Yin, Yu Sun, Hua Wu, Tingwen Liu
| Challenge: | Existing trajectory-level length penalties fail to effectively shorten reasoning length and degrade accuracy, as they treat all reasoning steps uniformly and lack fine-grained signals to distinguish redundancy from necessity. |
| Approach: | They propose a low-overhead process-supervised RL framework that leverages the model’s intrinsic attention signals for step-level credit assignment. |
| Outcome: | The proposed framework reduces reasoning length while improving performance across 9 benchmarks. |
Test of Time: Rethinking Temporal Signal of Benchmark Contamination (2026.acl-long)
Copied to clipboard
Terry Jingchen Zhang, Gopal Dev, Ning Wang, Max Obreiter, Punya Syon Pandey, Keenan Samway, Wenyuan Jiang, Yinya Huang, Bernhard Schölkopf, Mrinmaya Sachan, Zhijing Jin
| Challenge: | Existing work on benchmarks containing publicly available information has been interpreted as a temporal signal for benchmark contamination. |
| Approach: | They show that LLM-transformed questions can produce remarkably different temporal patterns compared to fill-in-the-blank questions directly retrieved from the very same documents. |
| Outcome: | The proposed model can produce different temporal patterns compared to fill-in-the-blank questions retrieved from the same documents. |
ExpSeek: Self-Triggered Experience Seeking for Web Agents (2026.findings-acl)
Copied to clipboard
Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, Yongbin Li
| Challenge: | Existing methods for integrating experience into web agents are struggling to adapt to dynamically changing contextual observations during agent-environment interaction. |
| Approach: | They propose a model that shifts experience toward step-level proactive seeking by estimating step- level entropy thresholds and designing step-Level tailored experience content. |
| Outcome: | The proposed model achieves 9.3% and 7.5% performance improvements on Qwen3-8B and 32B models across four challenging web agent benchmarks. |
RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation (2024.emnlp-demo)
Copied to clipboard
Xuanwang Zhang, Yun-Ze Song, Yidong Wang, Shuyun Tang, Xinfeng Li, Zhengran Zeng, Zhen Wu, Wei Ye, Wenyuan Xu, Yue Zhang, Xinyu Dai, Shikun Zhang, Qingsong Wen
| Challenge: | Existing research on Retrieval Augmented Generation (RAG) does not address the problem of hallucinations and real-time updating of knowledge. |
| Approach: | They propose a modular open-source library to equip LLMs with external knowledge. |
| Outcome: | The proposed approach reduces the need for expensive open-source tools and lacks fair comparisons between novel RAG algorithms. |
Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking (2024.findings-acl)
Copied to clipboard
Zefeng Zhang, Jiawei Sheng, Zhang Chuang, Liangyunzhi Liangyunzhi, Wenyuan Zhang, Siqi Wang, Tingwen Liu
| Challenge: | Existing methods to link ambiguous mentions to entities in multimodal knowledge graphs rely on partial correlations. |
| Approach: | They propose a framework that leverages multi-element correlations to bridge modality gap and enable fine-grained semantic matching by exploiting correlation between multimodal features and entities. |
| Outcome: | The proposed framework outperforms state-of-the-art models and confirms the effectiveness of the proposed method. |
Learning to Correct Noisy Labels for Fine-Grained Entity Typing via Co-Prediction Prompt Tuning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that noise correction in fine-grained entity typing improves quality of training samples. |
| Approach: | They propose a method that leverages multiple prediction results to correct noisy labels . they integrate prediction results and utilize a differentiated margin to identify inaccurate labels a . |
| Outcome: | The proposed model improves quality of training samples annotated using distant supervision, ChatGPT, and crowdsourcing. |
HyperMem: Hypergraph Memory for Long-Term Conversations (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to long-term memory management rely on pairwise relations, causing fragmented retrieval. |
| Approach: | They propose a hypergraph-based hierarchical memory architecture that explicitly models high-order associations using hyperedges. |
| Outcome: | Experiments show that HyperMem achieves state-of-the-art performance with 92.73% accuracy for long-term conversations. |
ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | NVFP4 supports fine-grained block isolation, 4-bit quantization errors and mixed-precision approaches . ARCQuant boosts NVFO4 performance via Augmented Residual Channels . |
| Approach: | They propose a framework that boosts NVFP4 performance via Augmented Residual Channels. |
| Outcome: | ARCQuant boosts NVFP4 performance via Augmented Residual Channels . the proposed framework achieves state-of-the-art accuracy comparable to full-precision baselines compared to FP16 . |
Improving Reasoning Capabilities in Small Models through Mixture-of-layers Distillation with Stepwise Attention on Key Information (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods focus on transferring teacher-generated rationales to student models, but do not explore teachers’ dynamic attention towards critical information during reasoning. |
| Approach: | They propose a method that transfers the teacher’s stepwise attention on key information to the student model and a Mixture of Layers module that allows dynamic alignment between the teacher and student. |
| Outcome: | The proposed framework achieves consistent performance improvements across multiple mathematical and commonsense reasoning datasets. |