China

With the rapid advancements in Large Language Models (LLMs), an increasing number of studies have leveraged LLMs as the cognitive core of agents to address complex task decision-making challenges. Specially, recent research has demonstrated the potential of LLM-based agents on automating GUI operations. However, existing methodologies exhibit two critical challenges: (1) static agent architectures struggle to adapt to diverse GUI application scenarios, leading to inadequate scenario generalization; (2) the agent workflows lack fault tolerance mechanism, necessitating complete process re-execution for GUI agent decision error. To address these limitations, we introduce COLA, a collaborative multi-agent framework for automating GUI operations. In this framework, a scenario-aware agent Task Scheduler decomposes task requirements into atomic capability units, dynamically selects the optimal agent from a decision agent pool, effectively responds to the capability requirements of diverse scenarios. Furthermore, we develop an interactive backtracking mechanism that enables human to intervene to trigger state rollbacks for non-destructive process repair. Experimental results on the GAIA dataset demonstrate COLA&#39;s notable performance among GUI Agent methods, achieving an average accuracy of 31.89%. Furthermore, our approach attained top results in the Web Browser (33.3%), Media &amp; Video (33.3%), and Windows Utils (25.0%) categories on WindowsAgentArena, highlighting the effectiveness of configuring specialized agents for each scenario and dynamically allocating strategies on demand. The code is available at https://anonymous.4open.science/r/COLA-demo-B8AB.

EMNLP 2025

COLA: Collaborative Multi-Agent Framework with Dynamic Task Scheduling for GUI Automation

llm multi agents

ai/llm agents

gui agents

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

With the rapid advancements in Large Language Models (LLMs), an increasing number of studies have leveraged LLMs as the cognitive core of agents to address complex task decision-making challenges. Specially, recent research has demonstrated the potential of LLM-based agents on automating GUI operations. However, existing methodologies exhibit two critical challenges: (1) static agent architectures struggle to adapt to diverse GUI application scenarios, leading to inadequate scenario generalization; (2) the agent workflows lack fault tolerance mechanism, necessitating complete process re-execution for GUI agent decision error. To address these limitations, we introduce COLA, a collaborative multi-agent framework for automating GUI operations. In this framework, a scenario-aware agent Task Scheduler decomposes task requirements into atomic capability units, dynamically selects the optimal agent from a decision agent pool, effectively responds to the capability requirements of diverse scenarios. Furthermore, we develop an interactive backtracking mechanism that enables human to intervene to trigger state rollbacks for non-destructive process repair. Experimental results on the GAIA dataset demonstrate COLA's notable performance among GUI Agent methods, achieving an average accuracy of 31.89%. Furthermore, our approach attained top results in the Web Browser (33.3%), Media & Video (33.3%), and Windows Utils (25.0%) categories on WindowsAgentArena, highlighting the effectiveness of configuring specialized agents for each scenario and dynamically allocating strategies on demand. The code is available at https://anonymous.4open.science/r/COLA-demo-B8AB.

technical paper

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Humans possess a unified cognitive ability to perceive, comprehend, and interact with the physical world. Why can't large language models replicate this holistic understanding? Through a systematic analysis of existing training paradigms in vision-language-action models (VLA), we identify two key challenges: \textit{spurious forgetting}, where robot training overwrites crucial visual-text alignments, and \textit{task interference}, where competing control and understanding tasks degrade performance when trained jointly. To overcome these limitations, we propose ChatVLA, a novel framework featuring Phased Alignment Training, which incrementally integrates multimodal data after initial control mastery, and a Mixture-of-Experts architecture to minimize task interference. ChatVLA demonstrates competitive performance on visual question-answering datasets and significantly surpasses state-of-the-art vision-language-action (VLA) methods on multimodal understanding benchmarks. Notably, it achieves a six times higher performance on MMMU and scores 47.2% on MMStar with a more parameter-efficient design than ECoT. Furthermore, ChatVLA demonstrates superior performance on 25 real-world robot manipulation tasks compared to existing VLA methods like OpenVLA. Our findings highlight the potential of our unified framework for achieving both robust multimodal understanding and effective robot control. \textcolor{blue}{\textit{The real robot video demo can be found at \href{https://anonymous.4open.science/r/ChatVLA-2F1C/ChatVLA_Demo.mp4}{video link}}}.

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model

Multimodal misinformation, encompassing textual, visual, and cross-modal distortions, poses an increasing societal threat that is amplified by generative AI. Existing methods typically focus on a single type of distortion and struggle to generalize to unseen scenarios. In this work, we observe that different distortion types share common reasoning capabilities while also requiring task-specific skills. We hypothesize that joint training across distortion types facilitates knowledge sharing and enhances the model’s ability to generalize. To this end, we introduce TRUST-VL, a unified and explainable vision-language model for general multimodal misinformation detection. TRUST-VL incorporates a novel Question-Aware Visual Amplifier module, designed to extract task-specific visual features. To support training, we also construct TRUST-Instruct, a large-scale instruction dataset containing 198K samples featuring structured reasoning chains aligned with human fact-checking workflows. Extensive experiments on both in-domain and zero-shot benchmarks demonstrate that TRUST-VL achieves state-of-the-art performance, while also offering strong generalization and interpretability.

TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection

The rapid advancement of Large Language Models (LLMs) has significantly enhanced performance across various natural language processing (NLP) tasks, yet the high computational costs and latency associated with deploying such models continue to pose critical bottlenecks, limiting their broader applicability. To mitigate these challenges, we propose a dynamic hybrid inference framework, Firewall Routing, which efficiently selects between a strong and a weak LLMs based on the complexity of the query. A lightweight routing model is trained to optimize resource allocation by learning from response quality and preventing long-tail queries, which are often too hard to solve by LLMs, from being routed to the stronger model. Moreover, our method incorporates multiple sampling to enhance query evaluation reliability while leveraging Hard Blocking and Soft Blocking to handle long-tail queries along with refining labels for model selection. Extensive experiments show our method outperforms existing routing strategies by up to 5.29\% in APGR, demonstrating state-of-the-art performance across multiple benchmarks.

Firewall Routing: Blocking Leads to Better Hybrid Inference for LLMs

Personal narratives are stories authors construct to make meaning of their experiences. Style, the distinctive way authors use language to express themselves, is fundamental to how these narratives convey subjective experiences. Yet there is a lack of a formal framework for systematically analyzing these stylistic choices. We present a novel approach that formalizes style in personal narratives as patterns in the linguistic choices authors make when communicating subjective experiences. Our framework integrates three domains: functional linguistics establishes language as a system of meaningful choices, computer science provides methods for automatically extracting and analyzing sequential patterns, and these patterns are linked to psychological observations. Using language models, we automatically extract linguistic features such as processes, participants, and circumstances. We apply our framework to hundreds of dream narratives, including a case study on a war veteran with post-traumatic stress disorder. Analysis of his narratives uncovers distinctive patterns, particularly how verbal processes dominate over mental ones, illustrating the relationship between linguistic choices and psychological states.

Formalizing Style in Personal Narratives

Large Reasoning Models (LRMs) perform strongly in complex reasoning tasks via Chain-of-Thought (CoT) prompting, but often suffer from verbose outputs, increasing computational overhead. Existing fine-tuning-based compression methods either operate post-hoc pruning, risking disruption to reasoning coherence, or rely on sampling-based selection, which fails to remove redundant content thoroughly. To address these limitations, this work begins by framing two key patterns of redundant reflection in LRMs—textitConfidence Deficit, wherein the model reflects on correct intermediate steps, and textitTermination Delay, where reflection continues after a verified, confident answer—through a confidence-guided perspective. Based on this, we introduce textbfConCISE (textbfConfidence-guided textbfCompression textbfIn textbfStep-by-step textbfEfficient Reasoning), a framework designed to generate concise reasoning chains, integrating textitConfidence Injection to boost reasoning confidence, and textitEarly Stopping to terminate reasoning when confidence is sufficient. Extensive experiments demonstrate that compared to baseline methods, fine-tuning LRMs on textbfConCISE-generated data yields a better balance between compression and task performance, reducing length by up to ～50\% under SimPO, while maintaining high task accuracy.

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning

Large Language Models (LLMs) show impressive inductive reasoning capabilities, enabling them to generate hypotheses that could generalize effectively to new instances when guided by in-context demonstrations. However, in real-world applications, LLMs' hypothesis generation is not solely determined by these demonstrations but is significantly shaped by task-specific model priors. Despite their critical influence, the distinct contributions of model priors versus demonstrations to hypothesis generation have been underexplored. This study bridges this gap by systematically evaluating three inductive reasoning strategies across five real-world tasks with three LLMs. Our empirical findings reveal that, hypothesis generation is primarily driven by the model's inherent priors; removing demonstrations results in minimal loss of hypothesis quality and downstream usage. Further analysis shows the result is consistent across various label formats with different label configurations, and prior is hard to override, even under flipped labeling. These insights advance our understanding of the dynamics of hypothesis generation in LLMs and highlight the potential for better utilizing model priors in real-world inductive reasoning tasks.

 On the Role of Model Prior in Real-World Inductive Reasoning

Reward models (RMs) are central to the alignment of language models (LMs). An RM often serves as a proxy for human preferences to guide downstream LM behavior. However, our understanding of RM behavior is limited. Our work (i) formalizes a framework for measuring the alignment of opinions on RMs, (ii) investigates the extent to which RMs demonstrate sociodemographic biases, and (iii) explores the effects of prompting to steer rewards towards the preferences of a target group. We study subjective opinions and diverse perspectives on controversial topics, through which we expect to quantify RM perspectives through their attitudes and values. We show that RMs are poorly aligned with several demographic groups and can systematically reward harmful stereotypes, and steering is not enough to overcome these limitations. Our findings underscore the need for more careful consideration of RM behavior in model alignment during preference learning to prevent the propagation of unwanted social biases in the language technologies we use.

Reward Model Perspectives: Whose Opinions Do Reward Models Reward?

Humans acquire syntactic constructions like filler–gap dependencies from limited and often noisy input. Can neural language models do the same? We investigate this question by evaluating GPT-2 models trained on child-directed input from the BabyLM Challenge. Our experiments focus on whether these “baby” language models acquire filler–gap dependencies, generalize across constructions, and respect structural constraints such as island effects. We apply a suite of syntactic constructions to four models trained on child language, including two base models (trained on 10M and 100M tokens) and two well-performing models from the BabyLM Challenge (ConcreteGPT and BabbleGPT). We evaluate model behavior using wh-licensing scores, flip tests, and grammaticality contrasts across four constructions. Results show that BabyLM-scale models partially acquire filler–gap dependencies but often fail to generalize or fully capture island constraints.

Mind the Gap: How BabyLMs Learn Filler-Gap Dependencies

We introduce a set of training-free ABX-style discrimination tasks to evaluate how multilingual language models represent language identity (form) and semantic content (meaning). Inspired from speech processing, these zero-shot tasks measure whether minimal differences in representation can be reliably detected. This offers a flexible and interpretable alternative to probing. Applied to XLM-R (Conneau et al, 2020) across pretraining checkpoints and layers, we find that language discrimination declines over training and becomes concentrated in lower layers, while meaning discrimination strengthens over time and stabilizes in deeper layers. We then explore probing tasks, showing some alignment between our metrics and linguistic learning performance. Our results position ABX tasks as a lightweight framework for analyzing the structure of multilingual representations.

Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks

Large language models (LLMs) increasingly power car assistants, enabling natural language interaction for tasks such as maintenance, troubleshooting, and operational guidance. While retrieval-augmented generation (RAG) improves grounding using vehicle manuals, evaluating response quality remains a key challenge. Traditional metrics like BLEU and ROUGE fail to capture critical aspects such as factual accuracy and information coverage. We propose GEAR, a fully automated, reference-based evaluation framework for car assistant systems. GEAR uses LLMs as evaluators to compare assistant responses against ground-truth counterparts, assessing coverage, correctness, and other dimensions of answer quality. To enable fine-grained evaluation, both responses are decomposed into key facts and labeled as essential, optional, or safety-critical using LLMs. The evaluator then determines which of these facts are correct and covered. Experiments show that GEAR aligns closely with human annotations, offering a scalable and reliable solution for evaluating car assistants.

Downloads

Next from EMNLP 2025

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model

Similar lecture

GUICourse: From General Vision Language Model to Versatile GUI Agent