United States

Large Language Models (LLMs) increasingly rely on agentic capabilities—iterative retrieval, tool use, and decision-making—to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as unstructured text and fail to leverage the topological dependencies inherent in real-world data. To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference. Specifically, we propose AgentGL, the first reinforcement learning (RL)–driven framework for AGL. AgentGL equips an LLM agent with graph-native tools for multi-scale exploration, regulates tool usage via search-constrained thinking to balance accuracy and efficiency, and employs a graph-conditioned curriculum RL strategy to stabilize long-horizon policy learning without step-wise supervision. Across diverse Text-Attributed Graph (TAG) benchmarks and multiple LLM backbones, AgentGL substantially outperforms strong GraphLLMs and GraphRAG baselines, achieving absolute improvements of up to 17.5% in node classification and 28.4% in link prediction. These results demonstrate that AGL is a promising frontier for enabling LLMs to autonomously navigate and reason over complex relational environments. The code is publicly available at \url{ https://github.com/sunyuanfu/AgentGL}.

ACL 2026

AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

poster

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.

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.

Multimodal Large Language Models (MLLMs) have been increasingly used as automatic evaluators—a paradigm known as *MLLM-as-a-Judge*. However, their reliability and vulnerabilities to biases remain underexplored. We find that many MLLM judges fail to reliably integrate key visual or textual cues, yielding unreliable evaluations when evidence is missing or mismatched, and exhibiting instability under semantically irrelevant perturbations. To address this, we systematically define *Compositional Bias* in MLLM-as-a-Judge systems and introduce **MM-JudgeBias**, a benchmark for evaluating it. MM-JudgeBias introduces controlled perturbations across Query, Image, and Response, and evaluates model behavior via two complementary metrics: *Bias-Deviation (BD)* for sensitivity and *Bias-Conformity (BC)* for stability. Our dataset of over 1,800 curated and refined multimodal samples, drawn from 29 source benchmarks, enables a fine-grained diagnosis of nine bias types across diverse tasks and domains. Experiments on 26 state-of-the-art MLLMs reveal systematic modality neglect and asymmetric evaluation tendencies, underscoring the need for more reliable judges.

MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge

In recent years, low-rank adaptation (LoRA) has emerged as a significant paradigm that freezes pre-trained weights and introduces small, learnable adapters instead of fine-tuning the full set of parameters. In this work, we uncover several key insights regarding the $\textit{singular}$ components of network parameters based on Singular Value Decomposition (SVD).
Firstly, the $\textit{principal}$ singular components with large singular values in pre-trained network parameters can be effectively reused during fine-tuning, whereas the $\textit{minor}$ components with smaller singular values are more task-specific and require substantial adaptation. Secondly, we first establish the theoretical connection that the uncontrolled growth of singular values in LoRA adapters leads to the forgetting of pre-trained knowledge — a well-known issue referred to as $\textit{catastrophic forgetting}$.
Building on these observations, we propose $\textbf{SCLoRA}$, which injects parameterized singular components with spectral clipping into the pre-trained model in a way that is aware of the spectral distribution of the pre-trained model. $\textbf{SCLoRA}$ effectively adapts to new tasks by focusing updates on components that require adaptation, while simultaneously alleviating catastrophic forgetting. We conduct extensive experiments and demonstrate that $\textbf{SCLoRA}$ not only improves downstream performance but also effectively retains pre-trained knowledge.

Can Spectral-Clipping Enable Better Learning While Forgetting Less for Low-Rank Adaptation?

Accurate assessment of critical thinking is historically limited by the Intention Behavior Gap in psychology: the disconnect between what individuals self-reported disposition and their actual practical behaviors. We try to bridge this gap with MASA (Multi-Agent Scenario-based Assessment), a framework that operationalizes cognitive assessment into an interpretable and interactive multi-agent workflow with Assessment Chain-of-Thought (AsCoT). Validating on both large-scale simulations (N=1,161) and human participants (N=70), we find that MASA aligns better with human expert ratings (r=0.882) than traditional gold-standard inventories (r=0.720), with an average cost of only $0.41 per participant. These results suggest that by shifting from self-report inventory to behavior-grounded dialogue, MASA offers a more accurate, cost-effective, and transparent solution for real-world cognitive evaluation.

 Beyond Self-Report: Bridging the Intention-Behavior Gap in Critical Thinking Assessment via Interpretable Multi-Agent System

Recent Large Reasoning Models (LRMs) have achieved remarkable progress, yet their evaluation still relies on a narrow paradigm: evaluating one question at a time. This single-question setup suffers from two major limitations: (1) vulnerability to data contamination and diminishing difficulty, forcing costly creation of new questions with significant human effort, (2) failure to evaluate models under multi-context pressure, a key requirement for real-world deployment. To bridge this gap, we present **REST** (Reasoning Evaluation through Simultaneous Testing), a stress-testing framework that exposes LRMs to multiple problems simultaneously. Beyond basic reasoning, REST evaluates two under-tested capabilities: *contextual priority allocation* and *robustness against contextual interference*. Our evaluation of more than **30** advanced reasoning models on **9** reasoning benchmarks reveals several striking findings: Even state-of-the-art (SOTA) models such as ***DeepSeek-R1 exhibit substantial performance degradation under stress testing***, challenging the prevailing assumption that "LLMs are multi-problem solvers". Crucially, ***REST demonstrates stronger discriminative power*** than existing benchmarks, revealing performance gaps among models that exhibit similar, near-ceiling performance under traditional evaluation. Some key insights emerge from our analysis: (1) the ***"overthinking trap"*** is a critical factor contributing to the performance degradation; (2) models trained with the ***"Long2Short" technique preserve more of their single-problem accuracy*** under REST, outperforming their standard-trained counterparts. These results establish REST as a cost-efficient, future-proof evaluation paradigm while reducing reliance on continuous human annotation. Code is available at https://github.com/opendatalab/REST.

REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once

Large Vision–Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook conflicts between visual and textual evidence and the importance of generating deflections (e.g., "Sorry, I cannot answer...") when retrieved knowledge is incomplete. These benchmarks also suffer from rapid obsolescence, as growing LVLM training sets allow models to answer many questions without retrieval. We address these gaps with three contributions. First, we propose a dynamic data curation pipeline that preserves benchmark difficulty over time by filtering for genuinely retrieval-dependent samples. Second, we introduce VLM-DeflectionBench, a benchmark of 2,775 samples spanning diverse multimodal retrieval settings, designed to probe model behaviour under conflicting or insufficient evidence. Third, we define a fine-grained evaluation protocol with four scenarios that disentangle parametric memorization from retrieval robustness. Experiments across 20 state-of-the-art LVLMs indicate that models usually fail to deflect in the presence of noisy or misleading evidence. Our results highlight the need to evaluate not only what models know, but how they behave when they do not, and serve as a reusable and extensible benchmark for reliable KB-VQA evaluation. All resources will be publicly available upon publication.

Benchmarking Deflection and Hallucination in Large Vision-Language Models

Existing hierarchical text classification (HTC) methods typically use prompt tuning or contrastive learning to inject the label hierarchy into a model as prior knowledge to implicitly learn label embeddings for classification. However, such implicit learning fails to accurately reflect label geometry (i.e., feature spatial distribution of label embeddings), as it does not model hierarchy-aware geometric relations among labels. To address this issue, we propose a novel two-stage label geometry structuring and aligning framework, termed LGSA, which transforms the label hierarchy from an implicit prior into an explicit embedding. First, we propose a hierarchical geometric structuring (HGS) module that leverages a general orthogonal frame (GOF) to reconstruct an explicit label geometry conforming to the label hierarchy. The label geometry is then treated as a label prototype to guide model training. To facilitate the guidance, we thereby propose a hierarchical geometric aligning (HGA) module as a regularization term to align label geometry learned by the model with the explicit label prototype. Experiments on three real-world HTC datasets confirm that LGSA consistently outperforms existing state-of-the-art methods. The code and models are available at https://anonymous.4open.science/r/LGSA-1E0C.

LGSA: Label Geometry Structuring and Aligning for Hierarchical Text Classification

Mainstream multilingual LLMs are generally trained on a much higher proportion of English than multilingual data, raising questions about their ability to capture linguistic features particular to non-English languages or to capture information important to non-anglophone cultures. We add to a growing effort to increase multilingual sensitivity in LLMs by developing a benchmark, EIFFEL, testing mastery of French idiomatic expressions in context. We fully explain the methodology, which exploits input from native French speakers, to make it reproducible for other languages. We compare mainstream multilingual LLMs with French-focused LLMs both on standard LLM benchmarks and EIFFEL; EIFFEL brings out the benefits of higher proportions of French data and shows limitations of standard benchmarks for measuring multilingual competence.

EIFFEL: a novel benchmark to measure bias of English heavy training on French idiomatic expressions

Extracting embeddings directly from Mixture-of-Experts (MoE) models is a promising yet underexplored direction that requires no additional data or fine-tuning. While previous studies have utilized semantic compression prompts or expert routing information to improve sentence embeddings, they typically allocate a fixed number of experts uniformly across all layers and tokens, ignoring inter-layer and inter-token heterogeneity. In this work, we identify two key observations in MoE models: (1) layer-wise variations in expert homogeneity, suggesting that different layers require different expert budgets, and (2) token-wise contribution imbalance, indicating that different tokens should also be allocated different numbers of experts. To address these issues, we propose an Adaptive Expert Allocation (AEA) framework that dynamically performs both layer-wise and token-wise expert allocation to enhance embedding quality. Specifically, AEA allocates fewer experts to layers with higher homogeneity and to tokens with lower attention importance, where layer-wise homogeneity is determined by the similarity among embeddings produced by the experts in each layer. Notably, our method is plug-and-play, seamlessly integrates with existing prompt engineering methods, and introduces no additional time overhead. Experiments on the STS tasks demonstrate that AEA consistently improves embedding quality across multiple MoE models.

AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM

Multimodal abductive reasoning — the generation and selection of explanatory hypotheses from partial observations — is a cornerstone of intelligence. Current evaluations of such ability in vision–language models (VLMs) are largely confined to static, single-agent tasks. Inspired by Dixit, we introduce DixitWorld, a comprehensive evaluation suite designed to deconstruct this challenge. DixitWorld features two core components: DixitArena, a dynamic, multi-agent environment that evaluates both hypothesis generation (a "storyteller" crafting cryptic clues) and hypothesis selection ("listeners" choosing the target image from decoys) under imperfect information; and DixitBench, a static QA benchmark that isolates the listener's task for efficient, controlled evaluation. Results from DixitArena reveal distinct, role-dependent behaviors: smaller open-source models often excel as creative storytellers, producing imaginative yet less discriminative clues, whereas larger proprietary models demonstrate superior overall performance, particularly as listeners. Performance on DixitBench strongly correlates with listener results in DixitArena, validating it as a reliable proxy for hypothesis selection. Our findings reveal a key trade-off between generative creativity and discriminative understanding in multimodal abductive reasoning, a central challenge for developing more balanced and capable vision-language agents.

DIXITWORLD: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay

Speculative decoding accelerates autoregressive generation by letting draft tokens bypass full verification, but conventional frameworks suffer from frequent false rejections, particularly when draft models produce semantically correct but lexically divergent outputs. In this paper, we present Calibrated Speculative Decoding (CSD), a training-free framework that recovers valid tokens discarded by standard verification. Guided by the principle of "Frequency-Guided Candidate Selection and Probability-Guarded Acceptance," CSD incorporates two lightweight modules: Online Correction Memory, which aggregates historical rejections to propose recurring divergence patterns as rescue candidates, and Semantic Consistency Gating, which verifies candidate admissibility using probability ratios instead of exact token matching. Our evaluation across diverse large language models demonstrates that CSD outperforms existing methods, achieving a peak throughput speedup of 2.33x. CSD preserves model accuracy across all tasks while further boosting performance on complex reasoning datasets. These results establish CSD as a highly effective, lightweight solution for practical LLM deployments.

Downloads

Next from ACL 2026

MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge

Similar lecture

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs