United States

Reinforcement learning (RL) has emerged as a powerful paradigm for improving the reasoning capabilities of large language models (LLMs). Despite its success, RL faces fundamental challenges, including low sample efficiency and a strong dependence on the quality of the base model: while some models improve rapidly with limited RL updates, others require substantial training data to achieve meaningful gains. Recent studies suggest that the patterns of thinking tokens play a critical role in RL performance, and that supervised fine-tuning (SFT) on datasets exhibiting desirable reasoning patterns can reduce reliance on base models and better prepare LLMs for RL. However, how to automatically discover such patterns across tasks remains unclear. In this work, we describe thinking token patterns with reasoning primitives and argue that initializing LLMs with diverse, high-quality primitives is crucial for stable and efficient RL training. We propose Tailor, a pipeline that automatically discovers such reasoning primitives and curates SFT datasets to prepare LLMs for RL. Extensive experiments on mathematical and logical reasoning benchmarks demonstrate that Tailor consistently improves downstream RL performance, outperforming strong baselines, including methods with expert domain knowledge.

ACL 2026

Tailored Primitive Initialization is the Secret Key to Reinforcement Learning

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.

**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.

technical paper

LLM-powered multi-agent systems (MAS) have demonstrated strong performance on complex tasks. However, most existing approaches still rely on hand-crafted communication protocols or automatically designed communication topologies, which generalize poorly across tasks. We introduce NeuralFSM, a state-driven framework that formulates multi-agent problem solving as a finite-state execution process. NeuralFSM learns both the state transition distribution and inter-agent communication weights from interaction traces using a Temporal Coordination Controller. Rather than prioritizing explicit structure generation, the proposed framework uses task context to modulate transition and routing decisions, enabling flexible coordination without manual protocol design. To improve robustness against noisy or adversarial agents, we incorporate graph regularization during training and apply trust-aware message attenuation at runtime. Experiments on diverse benchmarks show that NeuralFSM consistently outperforms prior baselines by an average margin of 6.74\%--19.39\%, while substantially reducing token consumption. Moreover, NeuralFSM exhibits strong inherent robustness, which is further enhanced by the protection layer, resulting in only a 1.82\% performance drop under attack.

NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy

With the generative capabilities of large language models (LLMs) reshaping the information ecosystem, the concern with the sociological validity of claim detection benchmarks is increasing. Current claim detection benchmarks predominantly treat claims as static textual artifacts, overlooking the sociological etiology of how information naturally emerges and mutates. In this paper, we propose an evolutionary paradigm that models claims as socially evolving entities. In specific, we introduce a socially generative framework for synthetic claim generation, a multi-agent simulation grounded in the Open Claims Model. By decomposing claims into context, utterance, and proposition, our approach enables the precise simulation of unmitigated propagation to capture truth decay, and intervened propagation with multi-auditor oversight for targeted generation. Furthermore, we propose the background-user-perspective (BUP) framework, which reformulates check-worthiness as a condition-dependent probability rooted in social environment. Experiments on our datasets verify the data quality and reveal how network topology and user attributes systematically shape veracity drift.

Beyond Static Artifacts: An Evolutionary Framework for Synthetic Claim Generation

As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in high-risk domains. 
However, existing benchmarks largely rely on mixed queries and posterior evaluation, output-level scoring, which quantifies hallucination severity but offers limited insight into where and why hallucinations arise in the generation pipeline. 
We therefore reformulate hallucination evaluation as a diagnostic problem and propose PRISM, a controlled benchmark 
that disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors, grounded in three stages of generation (memory, instruction, and reasoning). 
PRISM contains 9,448 instances across 65 tasks and supports fine-grained, stage-aware diagnostic evaluation. Evaluating 24 mainstream open-source and proprietary LLMs, we uncover consistent trade-offs across instruction following, memory retrieval, and logical reasoning, showing that mitigation strategies often improve specific dimensions at the expense of others.
We hope PRISM provides a framework for understanding the specific mechanisms behind LLMs hallucinations, ultimately accelerating the development of trustworthy large language models.

PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations

Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned) model. The implicit reward approach skews the large model distribution, whereas the nudging approach defers the generation of the next token to the small aligned model when the large base one is unconfident about its outcome. In this work, we first show that both approaches can be reduced to sampling from similar graphical models, where they differ only in the definition of a rejection criterion (or distribution). Moreover, we argue that the confidence criterion is ill-motivated due to linguistic phenomena like ambiguous phrasing. We propose a novel rejection criterion based on a conservative confidence bet. Experimentally, our novel approach outperforms previous work on several datasets.

On the Rejection Criterion for Proxy-based Test-time Alignment

In real-world business environments, data is stored in a variety of sources, including structured relational databases, semi-structured databases, and unstructured files. The ability to extract reasonable insights across these diverse sources is integral to data-driven decision-making. Existing benchmarks, however, are limited in assessing agents' capabilities across these diverse data types. To address this gap, we introduce UniDataBench, a multi-source benchmark designed to evaluate the performance of data analytics agents in handling diverse data sources. Specifically, UniDataBench is constructed based on real-life industry analysis reports, employing a pipeline to synthesize data that aligns with authentic analytical trends. It encompasses diverse datasets spanning relational databases, CSV files, and NoSQL stores to reflect real-world business settings, and provides a unified framework for evaluating how effectively agents can explore multiple data formats, extract insights, and generate meaningful summaries and recommendations. 
Based on UniDataBench, we propose a novel LLM-based agent named ReActInsight, an autonomous agent that performs end-to-end analysis over diverse data sources by automatically discovering cross-source linkages, decomposing goals, and generating robust, self-correcting code to extract actionable insights. Our benchmark and agent together provide a framework for facilitating the development of data analytics agents in real-world applications.

UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data

We introduce MMSciCode, a comprehensive expert-level, multilingual multi-discipline benchmark for evaluating foundation models in scientific code generation. It includes 624 expert-annotated research coding problems spanning six core scientific disciplines. Compared to prior benchmarks, MMSciCode features three key advancements. First, it challenges models to integrate domain-specific knowledge with algorithmic reasoning to implement core functions from research papers, moving beyond the isolated, general-purpose coding tasks typically assessed in current benchmarks. Second, each problem is meticulously annotated by domain experts through a rigorous paper-grounded process, with strict quality controls implemented to ensure dataset integrity and authenticity. Finally, each problem is equipped with comprehensive unit test suites and containerized environments, enabling reproducible and diagnostic evaluation of both functional correctness and domain validity. We conduct an extensive evaluation of 28 state-of-the-art foundation models and 2 agentic coding tools on MMSciCode. Our results reveal that even the best non-agentic model achieves only around 15\% accuracy, while the top agentic coding tool reaches 32.2\%, both still far below human expert performance of 68.8\%. Through comprehensive error analyses and case studies, we identify substantial performance gaps between models and human experts, providing actionable insights for advancing expert-level scientific code generation.

MMSciCode: Real-world Evaluation of Multilingual Multi-Discipline Scientific Research Coding

Intelligent dialogue systems are increasingly deployed in emotionally and ethically sensitive settings, where failures in either emotional attunement or ethical judgment can cause significant harm. Existing dialogue models typically address empathy and ethical safety in isolation, and often fail to adapt their behavior as ethical risk and user emotion evolve across multi-turn interactions. We formulate ethical-emotional alignment in dialogue as an explicit turn-level decision problem, and propose \textsc{EthicMind}, a risk-aware framework that implements this formulation in multi-turn dialogue at inference time. At each turn, \textsc{EthicMind} jointly analyzes ethical risk signals and user emotion, plans a high-level response strategy, and generates context-sensitive replies that balance ethical guidance with emotional engagement, without requiring additional model training. To evaluate alignment behavior under ethically complex interactions, we introduce a risk-stratified, multi-turn evaluation protocol with a context-aware user simulation procedure. Experimental results show that \textsc{EthicMind} achieves more consistent ethical guidance and emotional engagement than competitive baselines, particularly in high-risk and morally ambiguous scenarios.

EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue

To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates but remain vulnerable to interference from transient noise. Conversely, discrete structured memory architectures provide robust knowledge retention but often struggle to adapt to fluid narrative evolution. To address this, we propose GAM, a hierarchical Graph-based Agentic Memory framework that explicitly decouples memory encoding from consolidation to effectively resolve the conflict between rapid context perception and stable knowledge retention. By isolating ongoing dialogue in a event progression graph and integrating it into a topic associative network only upon semantic shifts, our approach minimizes interference while preserving long-term consistency. Additionally, we introduce a Graph-guided, Multi-factor Retrieval strategy to enhance context precision. Experiments on LoCoMo and LongDialQA benchmarks indicate that our method consistently outperforms state-of-the-art baselines in both reasoning accuracy and computational efficiency.

GAM: Hierarchical Graph-based Agentic Memory for LLM Agents

Neologisms, emerging terms in meaning or form, can serve as new vehicles for toxic expression, like "田园女" ("country girl") as a stigmatizing label targeting feminism. Such toxic neologisms appear benign but have evolved into toxic usage in public consensus, posing challenges to moderation systems and remaining underexplored. In this paper, we investigate how to detect implicit toxicity expressed via neologisms. We first propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms, followed by the construction of a lexicon spanning widely observed risk categories. To capture toxicity grounded in public consensus, we introduce **SeTox**, a search-augmented framework that enables static large language models (LLMs) to incorporate real-time web context for neologism toxicity detection. Experiments show that **SeTox**, even with 3B-scale models, outperforms recent large-scale models, demonstrating its scalability to incorporate real-world knowledge for toxic neologism detection. **Disclaimer**: this paper has offensive contents that may be disturbing to some readers.

New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs

Document-level relation extraction (DocRE) aims to determine which relations hold between a given entity pair within a document. As a multi-label classification task, the most commonly adopted paradigm introduces a learnable threshold to distinguish positive and negative classes for an entity pair. Under this paradigm, existing losses decouple the optimization into independent positive and negative losses, which interact solely with a shared threshold. This leads to two inherent limitations: (*i*) threshold instability caused by conflicting gradient updates from the decoupled losses; and (*ii*) optimization bias exacerbated by the severe imbalance between limited positive samples and abundant negative samples inherent in DocRE, which makes the model more likely to predict that no relation exists.

To address these issues, we propose the **A**daptive-**T**hreshold **G**lobal **L**oss (ATGL). Unlike prior work, ATGL integrates positive, negative, and threshold optimization into a unified logit space and explicitly enforces ranking constraints on their contributions to the objective. Furthermore, ATGL incorporates an imbalance-aware optimization mechanism, thereby effectively addressing the severe class imbalance in DocRE. Our ATGL serves as a general optimization objective that can be readily applied to different DocRE models. Experiments on four datasets show that ATGL outperforms other DocRE losses and achieves state-of-the-art results, while consistently improving the performance of existing DocRE models. Code is available at https://github.com/xhm-code/ATGL.

Downloads

Next from ACL 2026

NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy

Similar lecture

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models