United States

Current large language models (LLMs) and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn. This prevents the model from interacting with the user during the user&#39;s turn and can lead to high response latency when the model is thinking. To address this issue, we draw inspiration from the “think while listening” behavior of humans. In this paper, we propose SHANKS, a general inference framework that enables SLMs to generate unspoken chain-of-thought reasoning while listening to user input. SHANKS streams input speech in fixed-duration chunks and, as soon as a chunk is received, generates unspoken reasoning based on all previous speech and reasoning, while the user continues speaking. SHANKS uses unspoken reasoning to determine whether to interrupt the user and make tool calls to complete the task. We demonstrate that SHANKS enhances real-time user–SLM interaction in two scenarios: (1) SHANKS can listen to the user&#39;s speech and interrupt when the user makes a mistake. (2) In a tool-augmented dialogue scenario, SHANKS can complete 56.9% of the tool calls before the user ends their turn. Overall, SHANKS is a step toward models that keep thinking throughout the conversation, not only after a turn ends. Demos can be found on the project page: https://d223302.github.io/SHANKS/.

ACL 2026

Shanks: Simultaneous Hearing and Thinking for Spoken Language Models

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. <br>
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) <br><br><br>
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>
<br><br><br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to ACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

Registration Required

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

Current large language models (LLMs) and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn. This prevents the model from interacting with the user during the user's turn and can lead to high response latency when the model is thinking. To address this issue, we draw inspiration from the “think while listening” behavior of humans. In this paper, we propose SHANKS, a general inference framework that enables SLMs to generate unspoken chain-of-thought reasoning while listening to user input. SHANKS streams input speech in fixed-duration chunks and, as soon as a chunk is received, generates unspoken reasoning based on all previous speech and reasoning, while the user continues speaking. SHANKS uses unspoken reasoning to determine whether to interrupt the user and make tool calls to complete the task. We demonstrate that SHANKS enhances real-time user–SLM interaction in two scenarios: (1) SHANKS can listen to the user's speech and interrupt when the user makes a mistake. (2) In a tool-augmented dialogue scenario, SHANKS can complete 56.9% of the tool calls before the user ends their turn. Overall, SHANKS is a step toward models that keep thinking throughout the conversation, not only after a turn ends. Demos can be found on the project page: https://d223302.github.io/SHANKS/.

poster

Existing video summarization methods mainly compress content for gist browsing, but they often break the prerequisite logic in instructional videos and induce logical inversions (e.g., conclusions before premises). We formalize this problem as Structure-Pedagogical Reconstruction (SPR). SPR raises two challenges: (1) Structure Hallucination, where retrieved knowledge is topologically valid but not evidence-grounded by the blackboard; and (2) Logical Inversion, where soft prompt-level graph injection fails to enforce prerequisite order during decoding. To address these challenges, we propose Knowledge-Centric Video Reconstruction (KCVR), a Plan-then-Generate neuro-symbolic framework that decouples epistemic planning from content generation. KCVR prunes a Dual-Layer Epistemic Graph into a minimal video-supported plan, then realizes the plan with visually anchored attention and topology-constrained decoding. We additionally release EduStruct, a 10-discipline benchmark for SPR and structure-centric evaluation. Experiments show that KCVR outperforms strong end-to-end baselines on Knowledge Progression Consistency and Learning Objective Coverage. Our code and data are available at \url{https://github.com/mark1001-ljj/video_sum}.

 KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning

GUI agents have demonstrated remarkable progress in automating complex user interface interactions. However, training such agents for long-horizon tasks remains challenging. Single-turn reinforcement learning conditions on expert histories during training but self-generated histories during deployment, causing distribution mismatch. Online multi-turn methods eliminate this gap via environment interaction but suffer from sparse rewards and prohibitive costs. We propose $\underline{\textbf{E}}$xperience-driven $\underline{\textbf{M}}$ulti-turn $\underline{\textbf{P}}$olicy $\underline{\textbf{O}}$ptimization ($\textbf{EMPO}$), which leverages expert trajectories as environment experiences for on-policy multi-turn training. The agent constructs self-generated history throughout rollouts; when actions match expert experiences, the trajectory provides valid state transitions, and a Patch Module recovers mismatched steps to maintain on-policy rollouts. EMPO further incorporates discounted future rewards and dual-level advantage estimation to capture long-horizon dependencies. We also propose $\textbf{AndroidControl-Real}$, an evaluation metric strongly correlated with real-world performance (R$^2$=0.934). With only 1K public trajectories as RL experiences, our method achieves substantial gains over the base model (e.g., +12.0% on AndroidWorld and +23.8% on AITW) and achieves competitive performance against strong baselines such as UI-TARS-7B and GPT-4o, demonstrating better generalization than prior single-turn RL approaches. Code available: \url{https://anonymous.4open.science/r/UI-S1-0DAF}.

Experience-driven Multi-turn Reinforcement Learning for GUI Agents

Machine unlearning in multimodal large language models (MLLMs) aims to remove specific concepts while preserving overall utility. However, existing approaches focus primarily on general utility metrics, overlooking the preservation of semantically related concepts. We present the first systematic analysis of this proximal collateral damage, revealing that forgetting vulnerability correlates strongly with visual embedding similarity in a smooth gradient across the semantic space. Based on this insight, we propose a novel unlearning framework that introduces Self-Generated Proximal Visual Tokens (SGPVTs), which are synthetically perturbed visual representations around the target concept. Our method employs an adaptive cosine-band curriculum with a dual-stream objective: forgetting the target via gradient ascent while distilling knowledge from a frozen teacher model into proximal tokens to prevent degradation. Extensive experiments demonstrate that our approach significantly outperforms existing methods in preserving semantically related concepts while achieving effective target unlearning, eliminating the need for manual retention set curation. Our source code will be released in the near future.

 SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning

Enabling Large Language Models (LLMs) to effectively utilize tools in multi-turn interactions is essential for building capable autonomous agents. However, acquiring diverse and realistic multi-turn tool-use data remains a significant challenge. In this work, we propose a novel text-based paradigm. We observe that textual corpora naturally contain rich, multi-step problem-solving experiences, which can serve as an untapped, scalable, and authentic data source for multi-turn tool-use tasks. Based on this insight, we introduce GEM, a data synthesis pipeline that enables the generation and extraction of multi-turn tool-use trajectories from text corpora through a four-stage process: relevance filtering, workflow & tool extraction, trajectory grounding, and complexity refinement. To reduce the computational cost, we further train a specialized Trajectory Synthesizer via supervised fine-tuning. This model distills the complex generation pipeline into an efficient, end-to-end trajectory generator. Experiments demonstrate that our GEM-32B achieve a 14.9% improvement on the BFCL V3 Multi-turn benchmark. Our models partially surpass the performance of models trained on 
-bench (Airline and Retail) in-domain data, highlighting the superior generalization capability derived from our text-based synthesis paradigm. Notably, our Trajectory Synthesizer matches the quality of the full pipeline while significantly reducing inference latency and costs.

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Recent end-to-end spoken dialogue models enable natural interaction. However, as user demands become increasingly complex, models that rely solely on conversational abilities often struggle to cope. Incorporating agentic capabilities is therefore essential: by enabling tool use, these models can extend their knowledge boundaries and better solve real-world tasks. Yet, existing research has largely concentrated on core perception and generation, with comparatively limited exploration of such tool-augmented extensions. To bridge this gap, we present VoxMind, an integrated framework designed to equip end-to-end spoken dialogue models with comprehensive agentic abilities. Leveraging our curated 470-hour AgentChat dataset, we incorporate a "Think-before-Speak" mechanism, enabling the model to internalize structured reasoning as a critical prerequisite for planning and response generation. Furthermore, to mitigate latency bottlenecks caused by large-scale tool integration, we propose a Multi-Agent Dynamic Tool Management architecture. By asynchronously delegating retrieval tasks to an auxiliary agent aligned with the main model’s reasoning trajectory, this system effectively decouples inference latency from toolset size. Experimental results confirm that VoxMind achieves significant improvements in agent performance: compared with strong baselines, the task completion rate increases from 34.88% to 74.57%, outperforming Gemini-2.5-Pro on spoken agent tasks while preserving general conversational quality. The source code and associated data are publicly available at https://github.com/MM-Speech/VoxMind.

VoxMind: An End-to-End Agentic Spoken Dialogue System

Understanding complete musical scores entails integrated reasoning over pitch, rhythm, harmony, and large-scale structure, yet the ability of Large Language Models and Vision--Language Models to interpret full musical notation remains insufficiently examined.
We introduce Musical Score Understanding Benchmark (MSU-Bench), a human-curated benchmark for score-level musical understanding across textual (ABC notation) and visual (PDF) modalities. MSU-Bench contains 1,800 generative question--answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others, organised into four levels of increasing difficulty, ranging from onset information to texture and form. Evaluations of more than fifteen state-of-the-art models, in both zero-shot and fine-tuned settings, reveal pronounced modality gaps, unstable level-wise performance, and challenges in maintaining multilevel correctness. Fine-tuning substantially improves results across modalities while preserving general knowledge, positioning MSU-Bench as a robust foundation for future research in multimodal reasoning. The benchmark and code are available at https://github.com/Congren-Dai/MSU-Bench.

Musical Score Understanding Benchmark: Evaluating Large Language Models' Comprehension of Complete Musical Scores

The advancement of large language models (LLMs) has enhanced tabular question answering (Tabular QA), yet they struggle with open-domain queries exhibiting underspecified or uncertain expressions. To address this, we introduce the ODUTQA-MDC task and the first comprehensive benchmark to tackle it. This benchmark includes: (1) a large-scale ODUTQA dataset with 209 tables and 25,105 QA pairs; (2) a fine-grained labeling scheme for detailed evaluation; and (3) a dynamic clarification interface that simulates user feedback for interactive assessment. We also propose MAIC-TQA, a multi-agent framework that excels at detecting ambiguities, clarifying them through dialogue, and refining answers. Experiments validate our benchmark and framework, establishing them as a key resource for advancing conversational, underspecification-aware Tabular QA research.

ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification

Diffusion Large Language Models (dLLMs) deliver strong long-context processing capability in a non-autoregressive decoding paradigm. However, the considerable computational cost of bidirectional full attention limits the inference efficiency. Although sparse attention is promising, existing methods remain ineffective. This stems from the need to estimate attention importance for tokens yet to be decoded, while the unmasked token positions are unknown during diffusion. In this paper, we present **Focus-dLLM**, a novel training-free attention sparsification framework tailored for accurate and efficient long-context dLLM inference. Based on the finding that token confidence strongly correlates across adjacent steps, we first design a *past confidence-guided indicator* to predict unmasked regions. Built upon this, we propose a *sink-aware pruning strategy* to accurately estimate and remove redundant attention computation, while preserving highly influential attention sinks. To further reduce overhead, this strategy reuses identified sink locations across layers, leveraging the observed cross-layer consistency. Experimental results show that our method offers more than $29\times$ lossless speedup under $32K$ context length.

Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing

Scientific writing is an expert-domain task that demands deep domain knowledge, task-specific requirements and reasoning capabilities that leverage the domain knowledge to satisfy the task specifications. While scientific text generation has been widely studied, its evaluation remains a challenging and open problem. It is critical to develop models that can be reliably deployed for evaluating diverse open-ended scientific writing tasks while adhering to their distinct requirements. However, existing LLM-based judges and reward models are primarily optimized for general-purpose benchmarks with fixed scoring rubrics and evaluation criteria. Consequently, they often fail to reason over sparse knowledge of scientific domains when interpreting task-dependent and multi-faceted criteria. Moreover, fine-tuning for each individual task is costly and impractical for low-resource settings. To bridge these gaps, we propose cost-efficient, open-source reward models tailored for scientific writing evaluation. We introduce a two-stage training framework that initially optimizes scientific evaluation preferences and then refines reasoning capabilities. Our multi-aspect evaluation design and joint training across diverse tasks enable fine-grained assessment and robustness to dynamic criteria and scoring rubrics. Experimental analysis shows that our training regime strongly improves LLM-based scientific writing evaluation. Our models generalize effectively across tasks and to previously unseen scientific writing evaluation settings, allowing a single trained evaluator to be reused without task-specific retraining.

 Reward Modeling for Scientific Writing Evaluation

Online reinforcement learning (RL) serves as an effective method for enhancing the capabilities of Android agents. However, guiding agents to learn through online interaction is prohibitively expensive due to the high latency of emulators and the sample inefficiency of existing RL algorithms. We identify a fundamental limitation in current approaches: the Single State Single Action paradigm, which updates the policy with one-to-one state-action pairs from online one-way rollouts without fully exploring each costly emulator state. In this paper, we propose Android Coach, a novel framework that shifts the training paradigm to Single State Multiple Actions, allowing the agent to sample and utilize multiple actions for a single online state. We enable this without additional emulator overhead by learning a critic that estimates action values. To ensure the critic serves as a reliable coach, we integrate a process reward model and introduce a group-wise advantage estimator based on the averaged critic outputs. Extensive experiments demonstrate the effectiveness and efficiency of Android Coach: it achieves 7.5% and 8.3% success rate improvements on AndroidLab and AndroidWorld over UI-TARS-1.5-7B, and attains 1.4x higher training efficiency than Single State Single Action methods PPO and GRPO at matched success rates.

Downloads

Next from ACL 2026

KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning

Similar lecture

Thinking Alignment of Scenario-Oriented User Simulation