United States

Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed *LongTVQA* and *LongTVQA+* which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent.

ACL 2026

LongVideoAgent: Multi-Agent Reasoning with Long Videos

## 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*

EMNLP 2025

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

technical paper

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. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<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>

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 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.

**Online Registration Form**: https://acl.swoogo.com/acl2026

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.

We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning. Unlike existing VQA datasets that focus on coarse-grained categories and simple reasoning over single entities, M$^3$-VQA introduces diverse multi-entity questions involving multiple distinct entities from both visual and textual sources. It requires models to perform both sequential and parallel multi-hop reasoning across multiple documents, supported by traceable, detailed evidence and a curated multimodal knowledge base. We evaluate 16 leading MLLMs under three settings: without external knowledge, with gold evidence, and with retrieval-augmented input. The poor results reveal significant challenges for MLLMs in knowledge acquisition and reasoning. Models perform poorly without external information but improve markedly when provided with precise evidence. Furthermore, reasoning-aware agentic retrieval surpasses heuristic methods, highlighting the importance of structured reasoning for complex multimodal understanding. M$^3$-VQA presents a more challenging evaluation for advancing the multimodal reasoning capabilities of MLLMs. Our code and dataset are available at https://github.com/CASIA-IVA-Lab/M3VQA.

M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering

Generative Search Engines (GSEs) have reshaped information retrieval, and Generative Engine Optimization (GEO) emerges to improve the content visibility in GSEs' responses. Previous methods mainly rely on empirical strategies or query-dependent preferences of GSEs for content optimization. However, they remain limited in effectiveness as they overlook the latent user search demands in queries that drive content retrieval and response generation of GSEs. To address this, we propose Mind Reader, a novel GEO method to effectively improve the content visibility within the generated responses of GSEs through content optimization guided by the extracted latent demands of user search. Specifically, we propose a decomposition-recombination query augmentation module, which enriches the query with latent semantic information by decomposing it into diverse perspectives, capturing underlying semantic information, and recombining them into variants to support subsequent optimization. Then, we propose a reasoning coverage content optimization module. By optimizing content to cover critical reasoning information of GSEs, we align the content with the user search demands, effectively improving the content visibility. Extensive experiments on widely used GEO-Bench and our proposed PC-GEO show that our method significantly outperforms baselines and effectively improves content visibility (with up to 2.44x objective metrics and 1.23x subjective metrics on average).

Mind Reader: Latent User Demand-Guided Content Optimization for Generative Search Engine

Sign language research has achieved significant progress due to the advances in large language models (LLMs). However, the intrinsic ability of LLMs to understand sign language, especially in multimodal contexts, remains underexplored. To address this limitation, we introduce $\textbf{CNSL-bench}$, the first comprehensive $\textbf{C}$hinese $\textbf{N}$ational $\textbf{S}$ign $\textbf{L}$anguage $\textbf{bench}$mark designed for evaluating multimodal large language models (MLLMs) in sign language understanding. The proposed CNSL-bench is characterized by: 1) Authoritative grounding, as it is anchored to the officially standardized $\textit{National Common Sign Language Dictionary}$, mitigating ambiguity from regional or non-canonical variants and ensuring consistent semantic definitions; 2) Multimodal coverage, providing aligned textual descriptions, illustrative images, and sign language videos; and 3) Articulatory diversity, supporting fine-grained analysis across key manual articulatory forms, including air-writing, finger-spelling, and the Chinese manual-alphabet. Using CNSL-bench, we extensively evaluate 21 open-source and proprietary up-to-date MLLMs. Our results reveal that, despite recent advances in multimodal modeling, current MLLMs remain substantially inferior to human performance, exhibiting systematic disparities across input modalities and manual articulatory forms. Additional diagnostic analyses suggest that several performance limitations persist beyond improvements in reasoning and that instruction-following robustness varies substantially across models.

CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language

Self-report questionnaires remain the default tool for probing the psychological characteristics of Large Language Model (LLM) agents, yet classical instruments (BFI, BDI, MBTI, BSS) inherit three well-known threats under LLMs: contamination from training corpora, directional bias under social-desirability framing, and limited responsiveness to context beyond the item text. We ask whether a *projective* paradigm can be adapted into a usable psychometric tool for LLM agents. We introduce **GenPT** (Generative Projective Testing), which reformulates TAT, Rorschach, and SCT with newly generated stimuli and organises assessment as a three-stage pipeline (Behavior Collection $\to$ Interpretation $\to$ Diagnosis) grounded in SCORS-G and a Simplified Rorschach Analysis System. On personality traits (Big Five, MBTI) and mental-health risks (depression, suicide ideation), questionnaires exhibit systematic directional shifts under social-desirability framing, most strongly on suicide ideation, whereas GenPT's collected behavioral patterns stay near the symmetric baseline; under a longitudinal counselling context, GenPT-based depression assessment shifts by roughly an order of magnitude more than its questionnaire counterpart. Questionnaires remain competitive on clean-persona trait tasks where items align lexically with the persona description. Overall, GenPT complements rather than replaces self-report when contamination resistance, bias asymmetry, and context sensitivity matter. Code and stimuli: https://github.com/sci-m-wang/GenPT.

GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing

Current paradigms for empowering Large Language Models (LLMs) with multilingual capabilities rely heavily on massive instruction tuning. We challenge this view, proposing that the barrier is topological alignment, not data quantity. We introduce Hybrid Cross-Alignment (HCA), fusing a frozen NLLB encoder with a Qwen decoder via a closed-loop dual-adapter architecture. HCA utilizes a Source-Side Adapter to precondition encoder features and a Query-Residual Adapter to preserve generative stability, bridged by an adaptive gated cross-modal interface. Our core discovery is Universal Alignment Generalization.'' We demonstrate that training HCA on a single language pair (German-English) unlocks state-of-the-art zero-shot transfer to dozens of unseen languages. Crucially, our Oracle'' experiments reveal that this single-pair training recovers over 96.7% of the performance achievable by training on all available pairs. This proves that a universal, language-agnostic projection protocol exists. With a total inference footprint of 
5.25B parameters, our model significantly outperforms larger baselines, surpassing TowerPlus-9B (+9.0 COMET on low-resource languages) and Aya-101 (13B). Furthermore, performance scales linearly with encoder size; upgrading from 600M to 1.3B yields immediate gains (+3.4 points on Gujarati) with minimal retraining cost.

One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment

Large language models often display heterogeneous moral preferences across settings. We study inference-time steering toward a desired ethical framework while preserving general competence. We present Convergent-Divergent Routing, which traces and edits minimal branch points inside transformer blocks where ethical-framework-related pathways first converge and then diverge. Gating non-target branches at these loci blocks the downstream propagation while leaving upstream computations intact. We find that this intervention alone increases targeted ethical-framework reasoning. To achieve fine-grained control, we adapt Common Spatial Patterns to the residual stream and extract, for each branch-point layer, a pair of directions that discriminate between utilitarian and deontological frameworks. We then introduce Dual Logit Calibration, a closed-form, minimum-$\ell_2$-norm update that moves the residual within this two-dimensional subspace so the resulting directional projections align with user-specified preference weights. Experiments on real-life moral dilemmas show that our method reliably achieves preference calibration and largely preserves general capabilities, outperforming recent baselines while providing an interpretable mechanism.

Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models

Online sexism increasingly appears in subtle, context-dependent forms that evade traditional detection methods. Its interpretation often depends on overlapping linguistic, psychological, legal, and cultural dimensions, which produce mixed and sometimes contradictory signals in annotated datasets. These inconsistencies, combined with label scarcity and class imbalance, result in unstable decision boundaries and cause fine-tuned models to overlook subtler, underrepresented forms of harm. To address these challenges, we propose a two-stage framework that unifies (i) targeted training procedures to better regularize supervision to scarce and noisy data with (ii) selective, reasoning-based inference to handle ambiguous or borderline cases. First, we stabilize the training combining class-balanced focal loss, class-aware batching, and post-hoc threshold calibration, strategies for the firs time adapted for this domain to mitigate label imbalance and noisy supervision. Second, we bridge the gap between efficiency and reasoning with a a dynamic routing mechanism that distinguishes between unambiguous instances and complex cases requiring a deliberative process. This reasoning process results in the novel Collaborative Expert Judgment (CEJ) module which prompts multiple personas and consolidates their reasoning through a judge model. Our approach outperforms existing approaches across several public benchmarks, with F1 gains of +4.48% and +1.30% on EDOS Tasks A and B, respectively, and a +2.79% improvement in ICM on EXIST 2025 Task 1.1.

When in Doubt, Consult: Expert Debate for Sexism Detection via Confidence-Based Routing

The rapid growth of scientific literature has made it increasingly difficult for researchers to efficiently discover, evaluate, and synthesize relevant work. Recent advances in multi-agent large language models (LLMs) have demonstrated strong potential for understanding user intent and are being trained to utilize various tools.
In this paper, we introduce Paper Circle, a multi-agent research discovery and analysis system designed to reduce the effort required to find, assess, organize, and understand academic literature. The system comprises two complementary pipelines: (1) a Discovery Pipeline that integrates offline and online retrieval from multiple sources, multi-criteria scoring, diversity-aware ranking, and structured outputs; and (2) an Analysis Pipeline that transforms individual papers into structured knowledge graphs with typed nodes (e.g., concepts, methods, experiments, and figures) and edges, enabling graph-aware question answering and coverage verification. Both pipelines are implemented within a coder LLM–based multi-agent orchestration framework and produce fully reproducible, synchronized outputs (JSON, CSV, BibTeX, Markdown, and HTML) at each agent step. This paper describes the system architecture, agent roles, retrieval and scoring methods, knowledge graph schema, and evaluation interfaces that together form the Paper Circle research workflow. We benchmark Paper Circle on both paper retrieval and paper review generation, reporting hit rate, MRR, and Recall@K. Results show consistent improvements with stronger agent models. We have publicly released the website:https://papercircle.vercel.app/ and code: https://github.com/MAXNORM8650/papercircle.

Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework

Reinforcement learning with verifiable rewards is ideal for multi-constraint instruction following, yet standard group-relative policy optimization (GRPO) becomes unstable under discrete, low-dispersion rewards, where within-group reward distributions are frequently homogeneous. We identify and formalize three pathologies of z-score group normalization in this regime: low-variance amplification, mean-centering blindness, and zero-variance collapse. To address them, we propose MDP-GRPO, which stabilizes learning through (1) multi-temperature sampling to increase reward dispersion, (2) dual-anchor advantages to restore gradients in homogeneous groups, (3) prospect-theoretic shaping to bound updates and penalize violations based on Kahneman & Tversky's theory, and (4) asymmetric KL regularization. Evaluated on FollowBench, IFEval, and a curated multi-constraint dataset, MDP-GRPO outperforms standard GRPO, improving strict constraint satisfaction by up to 5.0\% on Llama-3.2-3B. Our method also enables stable convergence with small group sizes while preserving general capabilities on MMLU and ARC.

MDP-GRPO: Stabilized Group Relative Policy Optimization for Multi-Constraint Instruction Following

Concept Bottleneck Models (CBMs) predict through human-interpretable concepts, but they typically output point concept probabilities that conflate epistemic uncertainty (reducible model underspecification) with aleatoric uncertainty (irreducible input ambiguity). This makes concept-level uncertainty hard to interpret and, more importantly, hard to act upon. We introduce \modelname{} (Credal Ensemble Concept Estimation), a CBM framework that decomposes concept uncertainty by construction. \modelname{} represents each concept as a credal prediction (a probability interval), derives epistemic uncertainty from disagreement across diverse concept heads, and estimates aleatoric uncertainty via a dedicated ambiguity output trained to match annotator disagreement when available. The resulting signals support prescriptive decisions: automate low-uncertainty cases, prioritize data collection for high-epistemic cases, route high-aleatoric cases to human review, and abstain when both are high. Across several tasks, we show that epistemic uncertainty is positively associated with prediction errors, whereas aleatoric uncertainty closely tracks annotator disagreement, providing guidance beyond error correlation. Our implementation is available at the following link: https://github.com/Tankiit/Credal_Sets/tree/ensemble-credal-cbm

Downloads

Next from ACL 2026

M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering

Similar lecture

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction