Papers by Cong Wang

FastGAS: Fast Graph-based Annotation Selection for In-Context Learning (2024.findings-acl)

Challenge:	Automated Essay Scoring (AES) aims to evaluate the quality score of input essays without human intervention.
Approach:	They propose an unsupervised approach to evaluate the quality of input essays . they use multiple heuristic quality signals as pseudo-groundtruths to train a neural AES model .
Outcome:	The proposed approach achieves state-of-the-art performance on eight prompts of ASPA dataset compared with previous unsupervised methods .

Copied to clipboard

Zihan Chen, Song Wang, Cong Shen, Jundong Li

Low-Resource NLP

Challenge:	Existing methods to select unlabeled examples for annotation require a long time due to their complexity, hindering their practical viability.
Approach:	They propose a graph-based selection method to efficiently identify high-quality instances while minimizing computational overhead.
Outcome:	The proposed method significantly reduces selection time and improves performance on different tasks.

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network (2020.emnlp-main)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Ruipeng Jia, Yanan Cao, Hengzhu Tang, Fang Fang, Cong Cao, Shi Wang

Information Extraction & Text Mining

Challenge:	Existing extractive summarization methods focus on balancing salience and redundancy between sentences.
Approach:	They propose a hierarchical attentive heterogeneous graph for text summarization that models sentences . they propose to iteratively refine the sentence representations and deliver the labels by message passing .
Outcome:	The proposed method outperforms existing extractive summarization methods on large corpus.

Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs (2026.acl-long)

Copied to clipboard

Zifeng Cheng, Lingyun Qian, Zhiwei Jiang, Cong Wang, Yafeng Yin, Fei Shen, Ao Zhou, Qing Gu

Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models (2025.findings-acl)

Challenge:	Existing methods for extracting conditional text embeddings from large language models (LLMs) relying on prompts often fails to produce high-quality conditional embeddables, resulting in degradation of quality.
Approach:	They propose a plug-and-play method that constructs unconditional general text embeddings and uses them to refine conditional text embeds.
Outcome:	The proposed method improves performance of prompt-based methods on clustering, Semantic Textual Similarity, and triplet alignment datasets.

Copied to clipboard

Jiangxu Wu, Cong Wang, Tianhuang Su, Lin Haozhi, JunYang JunYang, Zhangchao Zhangchao, Binqiang Pan, SongpanYang SongpanYang, Mingpeng Mingpeng, Kai Shi, Zixian Li

Dialogue Systems & Conversational Agents

Challenge:	Existing methods for generating multi-turn dialogue data struggle to ensure both diversity and quality in instructions.
Approach:	They propose a framework that synthesizes multi-turn conversations through an iterative "Ask-Respond-Review" process involving three agent roles: a Candidate, multiple Reviewers, and a Chairman.
Outcome:	The proposed framework synthesizes multi-turn conversations through an iterative "Ask-Respond-Review" process involving three agent roles: a Candidate, multiple Reviewers, and a Chairman.

Mulan: A Multi-Level Alignment Model for Video Question Answering (2023.findings-emnlp)

Copied to clipboard

Yu Fu, Cong Cao, Yuling Yang, Yuhai Lu, Fangfang Yuan, Dakui Wang, Yanbing Liu

Visual Data in NLP

Challenge:	Existing methods focus on visual-language alignment at the video level, but they do not account for fine-grained semantic interaction between video and text.
Approach:	They propose a multi-level Alignment Model for Video Question Answering that establishes alignment between visual and textual modalities at the object-level, frame-level and video-level.
Outcome:	The proposed model outperforms state-of-the-art methods even with a small amount of extra visual-language pre-training data and a reduced number of trainable parameters.

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models (2025.findings-emnlp)

Copied to clipboard

Youan Cong, Pritom Saha Akash, Cheng Wang, Kevin Chen-Chuan Chang

Towards Provably Secure Generative AI: Reliable Consensus Sampling (2026.findings-acl)

Challenge:	Extract-Refine-Retrieve-Read is a query optimization framework for large language models . it is designed to bridge the pre-retrieval information gap in Retriev-Augmented Generation systems .
Approach:	They propose a framework to extract parametric knowledge from Large Language Models and refine them using a specialized query optimizer.
Outcome:	The extract-refine-retrieve-read framework outperforms baselines on QA datasets . it is designed to meet the knowledge requirements of large language models (LLMs)

Copied to clipboard

Yu Cui, Hang Fu, Sicheng Pan, Zhuoyu Sun, Yifei Liu, Yuhong Nie, Bo Ran, Baohan Huang, Xufeng Zhang, Haibin Zhang, Cong Zuo, Licheng Wang

Open-World Authorship Attribution (2025.findings-acl)

Challenge:	Existing research on generative AI security is driven by mutually reinforcing attack and defense methodologies grounded in empirical experience.
Approach:	They propose a new algorithm that uses a random sampling algorithm to control risk.
Outcome:	The proposed algorithm improves robustness and utility while maintaining latency comparable to existing algorithms.

Copied to clipboard

Xinhao Tan, Songhua Liu, Xia Cong, Kunjun Li, Xinchao Wang

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Challenge:	Existing benchmarks for large language models do not evaluate their performance in academic research . authors aim to identify authors from anonymous text without additional information .
Approach:	They propose a benchmark to quantitatively assess LLMs' ability to infer author from text . they propose 'open-world' authorship attribute' to be a two-stage framework .
Outcome:	The proposed approach achieves 60.7% accuracy and 44.3% accuracy in two stages.

Copied to clipboard

Zhiyu Yang, Zihan Zhou, Shuo Wang, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Pengyuan Liu, Dong Yu, Zhiyuan Liu, Xiaodong Shi, Maosong Sun

Multimodality

Challenge:	Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach:	They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome:	The proposed framework improves performance of commercial and open-source models.

SimPBL: A Multi-Agent Framework for Project-Based Learning (2026.acl-long)

Copied to clipboard

Daniel Zhang-Li, Joy Jia Yin Lim, Binglin Liu, Shangqing Tu, Zijun Yao, Hao Peng, Jifan Yu, Haoxuan Li, Zhanxin Hao, Ye He, Zekun Li, Jiangyi Wang, Lei Hou, Bin Xu, Xin Cong, Zhiyuan Liu, Huiqin Liu, Yu Zhang, Juanzi Li

Challenge:	Existing LLMs provide partial assistance without modeling these roles, and overly comprehensive help can reduce learner autonomy.
Approach:	They propose a multi-agent framework with an orchestrator agent that provides adaptive scaffolding from interaction logs and collaborator agents that support project work through boundary-aware collaboration.
Outcome:	The proposed framework improves learner examination scores by 14% . it is based on a multi-agent framework with an orchestrator agent .

DeMAC: Enhancing Multi-Agent Coordination with Dynamic DAG and Manager-Player Feedback (2025.findings-emnlp)

Copied to clipboard

Yuhan Liu, Cong Xu, Lu Liu, Yihua Wang, Feiyu Chen, Qi Jia, Yaqian Zhao, Zhichun Wang, Xiang Li

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Multi-agent systems (MAS) powered by large language models struggle to adapt to evolving task dependencies and to handle uncertainties.
Approach:	They propose a Dynamic Environment-Aware Manager-Player Agents Coordination framework that enhances multi-agent coordination through long-term strategic planning.
Outcome:	The proposed framework outperforms traditional reinforcement learning and human-agent collaboration in the Overcooked simulation.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

Multimodality

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism (2026.acl-long)

Copied to clipboard

Yuhao Shen, Tianyu Liu, Junyi Shen, Jinyang Wu, Quan Kong, Huan Li, Cong Wang

Information Retrieval

Challenge:	Parallel Speculative Decoding (PSD) has limitations due to speedup limits and high computational waste . a novel synchronous mechanism solves the Retrieval Precision-Efficiency Dilemma .
Approach:	They propose a framework that combines a draft-verification-based approach with a synchronous mechanism to solve the Retrieval Precision-Efficiency Dilemma.
Outcome:	The proposed framework breaks speedup limits for Speculative Decoding by overlapping draft generation with verification.

Adaptive Gating in Mixture-of-Experts based Language Models (2023.emnlp-main)

Copied to clipboard

Jiamin Li, Qiang Su, Yitao Yang, Yimin Jiang, Cong Wang, Hong Xu

Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering (2025.acl-long)

Challenge:	Existing models employ a fixed gating network where each token is computed by the same number of experts.
Approach:	They propose a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution.
Outcome:	The proposed model reduces training time and inference quality while maintaining sparsity while maintaining inference accuracy.

Copied to clipboard

Zifeng Cheng, Zhonghui Wang, Yuchen Fu, Zhiwei Jiang, Yafeng Yin, Cong Wang, Qing Gu

Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs (2025.findings-acl)

Challenge:	Existing studies focus on prompt engineering to encode the full semantics of a sentence into the embedding of the last token.
Approach:	They propose a technique that introduces an extra auxiliary prompt to elicit better sentence embedding . they propose to use the hidden state of the token as the sentence embedded in LLMs .
Outcome:	The proposed technique can improve performance of existing prompt-based methods on STS tasks and downstream classification tasks.

Copied to clipboard

Runchu Tian, Yanghao Li, Yuepeng Fu, Siyang Deng, Qinyu Luo, Cheng Qian, Shuo Wang, Xin Cong, Zhong Zhang, Yesai Wu, Yankai Lin, Huadong Wang, Xiaojiang Liu

Challenge:	Positional biases in large language models hinder their ability to process long inputs.
Approach:	They propose a benchmark to assess positional bias in large language models involving multiple pieces of relevant information.
Outcome:	The proposed benchmark assesses the performance of long-context language models by examining their models with different input lengths and tasks.

Universal Information Extraction with Meta-Pretrained Self-Retrieval (2023.findings-acl)

Copied to clipboard

Xin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, Bin Wang

From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning (2025.findings-emnlp)

Challenge:	Existing methods for IE are task-specific, resulting in specialized and isolated approaches for different tasks.
Approach:	They propose a method to retrieve task-specific knowledge from pretrained language models to enhance universal IE by using a Meta-Pretraining Algorithm.
Outcome:	The proposed method achieves the new state-of-the-art on 4 IE tasks, 12 datasets under fully-supervised, low-resource and few-shot scenarios.

Copied to clipboard

Zihan Chen, Song Wang, Xingbo Fu, Chengshuai Shi, Zhenyu Lei, Cong Shen, Jundong Li

Low-Resource NLP

Challenge:	In-context learning (ICL) enables large language models to perform novel tasks without parameter updates by conditioning on a few input-output examples.
Approach:	They propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling.
Outcome:	The proposed pipeline reduces reliance on LLMs for data labeling . it leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances.

Few-Shot Event Detection with Prototypical Amortized Conditional Random Field (2021.findings-acl)

Copied to clipboard

Xin Cong, Shiyao Cui, Bowen Yu, Tingwen Liu, Wang Yubin, Bin Wang

Information Extraction & Text Mining

Challenge:	Existing approaches to event detection ignore the trigger discrepancy and cause errors.
Approach:	They propose a unified model which converts a few-shot tagging problem into a single-shot model by using a Gaussian distribution.
Outcome:	The proposed model performs better than existing identifythen-classify models on a few-shot tagging problem with a double-part taging scheme.

Experiential Co-Learning of Software-Developing Agents (2024.acl-long)

Copied to clipboard

Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression (2026.acl-long)

Challenge:	Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents.
Approach:	They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution.
Outcome:	The proposed framework enables agents to tackle unseen software-developing tasks more effectively.

Copied to clipboard

Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang, Shengchao Liu, Guoxin Ma, Yu Lan, Cong Wang, Chao Shen

VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models (2025.emnlp-main)

Challenge:	Existing work on reducing CoT generation in reasoning impairs the necessary information for deriving the correct answer.
Approach:	They propose a reasoning paradigm that takes CoT as a part of context to simplify the reasoning task for Large Language Models (LLMs).
Outcome:	The proposed framework reduces the generation length of LLMs, but its effectiveness hinges on the efficiency and reliability of the contextual CoT generation.

Copied to clipboard

Bingrui Sima, Linhua Cong, Wenxuan Wang, Kun He

H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)

Challenge:	Recent advances in Large Reasoning Models (LRMs) have enabled sophisticated visual reasoning capabilities by integrating reinforcement learning and Chain-of-Thought (CoT) supervision.
Approach:	They propose a jailbreak framework that exploits visual reasoning chains to bypass safety mechanisms.
Outcome:	The proposed framework achieves high attack success rates on leading closed-source MLRMs.

Copied to clipboard

Yuhan Liu, Cong Xu, Qi Jia, Yihua Wang, Feiyu Chen, Liang Jin, Lu Liu, Yaqian Zhao, Yuting Ding, Xiang Li

Challenge:	Multi-tenant Model-as-a-Service (MaaS) workloads exhibit non-stationarity across multiple time scales . existing request schedulers often rely on a fixed policy that remains unchanged at runtime .
Approach:	They propose a hierarchical multi-agent scheduler that operates in a layered closed loop . they propose to maintain 1.2–3.0 higher Goodput than SGLang and vLLM .
Outcome:	Experiments show that H-MAS achieves 1.2–3.0 higher Goodput than SGLang and vLLM . it maintains more stable QoS under diverse request lengths and heterogeneous SLO targets .

Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger (2025.acl-long)

Copied to clipboard

Wenjun Li, Dexun Li, Kuicai Dong, Cong Zhang, Hao Zhang, Weiwen Liu, Yasheng Wang, Ruiming Tang, Yong Liu

SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)

Challenge:	Existing research expands the tool arrays of large language models (LLMs), but the necessity of using these tools is often overlooked, leading to indiscriminate tool invocation.
Approach:	They propose a meta-cognition proxy proxy for LLMs self-assessment of their capabilities, reflecting the model’s awareness of its own limitations.
Outcome:	The proposed strategy is fine-tuned-free and costs minimal.

Copied to clipboard

Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang

AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM (2026.acl-long)

Challenge:	Large language models (LLMs) have many advantages but they also pose significant safety risks.
Approach:	They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions .
Outcome:	The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets.

Copied to clipboard

Shufan Yang, Zifeng Cheng, Zhiwei Jiang, Qingfeng Qi, Yafeng Yin, Cong Wang, Ao Zhou, Qing Gu

CHOIR: Harmonizing Structured Persona Diversity for Robust Collaborative LLM Reasoning (2026.acl-long)

Challenge:	Existing methods to improve embeddings from Mixture-of-Experts models allocate a fixed number of experts uniformly across all layers and tokens, ignoring inter-layer and inter-token heterogeneity.
Approach:	They propose an Adaptive Expert Allocation framework that performs layer-wise and token-wise expert allocation to enhance embedding quality.
Outcome:	The proposed method improves embedding quality across multiple MoE models.

Copied to clipboard

Xiangjue Dong, Cong Wang, Maria Teleki, Millennium Bismay, Ruihong Huang, James Caverlee

RoDEval: A Robust Word Sense Disambiguation Evaluation Framework for Large Language Models (2025.emnlp-main)

Challenge:	Persona-assigned Large Language Models can be useful for personalized, context-aware reasoning.
Approach:	They propose a framework that harmonizes demographic perturbations into a unified prediction by balancing agreement and divergence among counterfactual personas.
Outcome:	The proposed framework improves reasoning performance even when base personas are suboptimal.

Copied to clipboard

Luyang Zhang, Shuaimin Li, Yishuo Li, Kunpeng Kang, Kaiyuan Zhang, Cong Wang, Wenpeng Lu

Bridging Kernel Drivers and Virtual Device Models with LLM-Powered Automation (2026.acl-demo)

Challenge:	Existing studies rely on single-task evaluations and classification-based metrics that overlook the fundamental differences between generative LLMs and traditional classification models.
Approach:	They propose to use four new metrics to evaluate LLM-based word sense disambiguation (WSD) . experimental results reveal significant limitations in LLMs' WSD performance .
Outcome:	The proposed evaluation framework is open-source at https://github.com/DayDream405/RoDEval.

Copied to clipboard

Mingyu Wang, Bin Yu, Wenjian Lu, Zhi Wang, Gao Kefeng, Cheng Wen, Xu Lu, Cong Tian

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation (2025.emnlp-main)

Challenge:	Linux kernel device drivers are tightly coupled with hardware, making them difficult to execute and test without physical devices.
Approach:	They present a tool that generates QEMU-based virtual devices directly from Linux driver source code.
Outcome:	The proposed tool generates QEMU-based virtual devices directly from Linux driver source code.

Copied to clipboard

Song Wang, Zihan Chen, Peng Wang, Zhepei Wei, Zhen Tan, Yu Meng, Cong Shen, Jundong Li

Text Clustering

Challenge:	Large language models (LLMs) lack robustness in knowledge-intensive tasks due to noisy or irrelevant retrieved data.
Approach:	They propose a multi-agent debate-based RAG framework that integrates external knowledge sources into large language models to improve their accuracy.
Outcome:	The proposed framework is unsupervised and leverages pretrained LLMs without fine-tuning, making it easily adaptable to various tasks.

Multi-Prompting Decoder Helps Better Language Understanding (2025.findings-acl)

Copied to clipboard

Zifeng Cheng, Zhaoling Chen, Zhiwei Jiang, Yafeng Yin, Cong Wang, Shiping Ge, Qing Gu

ToolDNA: Autonomous Evolution of Tool Metadata for Robust Dialogue Agents (2026.findings-acl)

Challenge:	Existing methods to adapt Pre-trained Language Models to downstream tasks are limited by their inference APIs.
Approach:	They propose a multi-prompting decoding framework that query PLMs with multiple prompts . they propose to query Plms with optimal transport for hidden states and calibrated decoding for class scores .
Outcome:	The proposed framework achieves state-of-the-art results on multiple natural language understanding datasets under the few-shot setting.

Copied to clipboard

Qiuyuan Ai, Cong Wang, Jiaqi Zhang, Zengxin Han, Jie Song

See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs (2026.acl-long)

Challenge:	Task-oriented dialogue systems face labor-intensive manual metadata tuning and sparse reinforcement learning (RL) rewards that fail to diagnose invocation errors.
Approach:	They propose a framework that enables auto-evolution of policy networks and tool metadata via RL . a tool metadata loop coordinates metadata through policy-generated candidates during rollouts .
Outcome:	The proposed framework achieves +11% problem resolution and +54% accuracy over commercial LLMs with prompt engineering and +25%/+35% over supervised fine-tuning.

Copied to clipboard

Yicheng Ji, Jun Zhang, Jinpeng Chen, Cong Wang, Lidan Shou, Gang Chen, Huan Li

Multimodality

Challenge:	Existing methods for video understanding suffer from autoregressive generation of tokens.
Approach:	They propose a training-free loosely SD framework for Video-LLMs that uses visual-relevant tokens to accurately pinpoint the latter.
Outcome:	The proposed framework boosts the accepted length and speedup ratio by 136% and 35% compared to SOTA training-free SD methods for Video-LLMs.

Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Copied to clipboard

Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun

Free-MAD: Consensus-Free Multi-Agent Debate (2026.findings-acl)

Challenge:	Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach:	They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome:	The proposed system outperforms baselines in the open domain task-solving benchmark.

Copied to clipboard

Yu Cui, Hang Fu, Haibin Zhang, Licheng Wang, Cong Zuo

Reasoning

Challenge:	Existing multi-agent debate methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is decided by majority voting in the last round.
Approach:	They propose a multi-agent debate framework that eliminates the need for consensus among agents and reconstructs the debate phase by introducing anti-conformity.
Outcome:	Experiments on eight benchmark datasets show that Free-MAD significantly improves reasoning performance while requiring only a single-round debate and thus reducing token costs.

ModularMoE: Fast LLM Customization with Parameter-Sharing Mixture-of-Experts for Low-Resource Settings (2026.findings-acl)

Copied to clipboard

Jiaxing Liu, Qi Qi, Haifeng Sun, Dunjun Li, Zirui Zhuang, Bo He, Xiang Yang, Cong Liu, Jianxin Liao, Jingyu Wang