United States

We demonstrate Hindsight, a working memory system for AI agents that organizes long-term memory into four logical networks and exposes three core operations. The world, experience, observation, and opinion networks separate objective facts from subjective beliefs, giving developers clear visibility into what an agent knows versus what it believes. The retain, recall, and reflect operations handle memory ingestion, retrieval, and reasoning respectively. The retrieval layer combines vector search, keyword matching, graph traversal, and temporal filtering in a parallel pipeline backed by PostgreSQL with pgvector. Unlike existing memory systems such as MemGPT, Zep, and Mem0, Hindsight is the only system that jointly provides fact-belief separation, temporal entity graphs, evolving opinions with confidence scores, and configurable behavioral profiles. On the LongMemEval and LoCoMo benchmarks, Hindsight with a 20B open-source model achieves 83.6% and 83.2% accuracy, outperforming full-context GPT-4o and all prior memory systems; with Gemini-3 Pro, accuracy reaches 91.4% on LongMemEval. Our interactive demonstration lets users build memory graphs through multi-session conversations, inspect how memories are classified across networks, and observe how agent opinions form and change over time. The system is $\textbf{open-source under the MIT license}$ and available as a Python package (pip install hindsight-all) and Docker image, with $\textbf{1.9K GitHub stars}$ and 191 forks till date.A video demo is at https://youtu.be/4M2wS-yEmVA.

ACL 2026

Hindsight: Structured Agent Memory that Retains, Recalls, and Reflects

### Looking for Cogsci 2023? Please [click here](https://underline.io/events/405/reception) to switch to 2023 edition.


**Dear Colleagues,**

Welcome to the 43rd Annual Conference of the Cognitive Science Society! 

This year’s conference brings together the latest research from all Cognitive Science and also highlights this year’s theme **Comparative Cognition: Animal Minds.** 

The program features four plenary speakers: Friederike Range (University of Veterinary Medicine, Vienna), Onur Güntürkün (Ruhr University Bochum), Julia Fischer (University of Göttingen), and Erich Jarvis (The Rockefeller University). The keynotes and invited symposia showcase the broad spectrum of ideas that encompass the conference theme of comparative cognition. 

Further, the program includes the Rumelhart Prize keynote presentation by Susan Goldin-Meadow (University of Chicago), and symposia to celebrate the winner of the Elman Prize: Wei Ji Ma (New York University), the Heineken Award winner Robert Zatorre (McGill University), and the Robert J. Glushko Dissertation Prizes session.

The program committee for CogSci 2021 received 1,025 submissions, including 710 full papers, 275 member abstracts, 8 publication-based talks, as well as 15 proposals for symposia, and 17 for workshops and tutorials. After a rigorous review process, the committee selected 152 papers for oral presentation and inclusion in the conference proceedings (14.8%), 332 papers for poster presentation and inclusion in the proceedings (32.4%), and 175 papers for poster presentation with inclusion of abstracts in the proceedings (17.1%) We also selected 275 submitted member abstracts. In addition, we accepted 6 publication-based talks, 12 symposia, and 9 workshops and tutorials to make for an exciting and inclusive program.

We hope that you enjoy the conference this year!<br><br>

**Your Program Chairs,**
![](https://assets.underline.io/uploads/markdown_image/1/image/99984908caba5e6453e5fc5ba34f3507.jpg)

**Learn more about the Vienna Cognitive Science Hub at the University of Vienna, hosts of CogSci 2021**

<iframe width="560" height="315" src="https://www.youtube.com/embed/464h1m3iU68" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>

To review the proceedings for the conference or review the searchable program, please visit the [website](https://cognitivesciencesociety.org/program/).


CogSci 2021

The Cognitive Science Society brings together researchers from around the world who hold a common goal: understanding the nature of the human mind. The mission of the Society is to promote Cognitive Science as a discipline, and to foster scientific interchange among researchers in various areas of study, including Artificial Intelligence, Linguistics, Anthropology, Psychology, Neuroscience, Philosophy, and Education. The Society is a non-profit professional organization and its activities include sponsoring an annual conference and publishing the journals Cognitive Science and TopiCS.

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. <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.

Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback for both RL training and evaluation. However, existing systems fail to provide accurate verification and efficiency under high-concurrency workloads. We present ScaleBox, a high-fidelity and scalable system designed to address these limitations in large-scale code training. ScaleBox introduces automated special-judge generation and management, fine-grained parallel execution across test cases with seamless multi-node coordination, and a configuration-driven evaluation suite for reproducible benchmarking. A series of experiments demonstrates that ScaleBox significantly enhances code verification accuracy and efficiency. Our further RLVR experiments show that ScaleBox substantially improves both performance on LiveCodeBench and training stability, significantly outperforming heuristic-matching baselines. By providing a reliable and high-throughput infrastructure, ScaleBox facilitates more effective research and development in large-scale code training.

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models

Checklists have emerged as a popular approach for interpretable and fine-grained evaluation, particularly with LLM-as-a-Judge. 
Beyond evaluation, these structured criteria can serve as signals for model alignment, reinforcement learning, and self-correction. To support these endeavors, we present $\texttt{AutoChecklist}$, an open-source library that unifies checklist-based evaluation into composable pipelines. At its core is a taxonomy of five checklist generation abstractions, each encoding a distinct strategy for deriving evaluation criteria. A modular $\textit{Generator $\rightarrow$ Refiner $\rightarrow$ Scorer}$ pipeline connects any generator with a unified scorer, and new configurations can be registered via prompt templates alone. The library ships with eight built-in pipelines implementing published approaches and supports multiple LLM providers (OpenAI, OpenRouter, vLLM). Beyond the Python API, the library includes a CLI for off-the-shelf evaluation and a web interface for interactive exploration. Validation experiments confirm that these checklist methods significantly align with human preferences and quality ratings, and a case study on ICLR peer review rebuttals demonstrates flexible domain adaptation. $\texttt{AutoChecklist}$ is publicly available at https://github.com/ChicagoHAI/AutoChecklist.

AutoChecklist: Composable Pipelines for Checklist Generation and Scoring with LLM-as-a-Judge

Over the past years, Automated Essay Scoring (AES) systems have gained increasing attention as scalable and consistent solutions for assessing proficiency of student writing. Despite recent progress, support for Arabic AES remains limited due to linguistic complexity and scarcity of large publicly-available annotated datasets. In this work, we present Qayyem, a Web-based platform designed to support Arabic AES by providing an integrated workflow for assignment creation, batch essay upload, scoring configuration, and per-trait essay evaluation. Qayyem abstracts the technical complexity of interacting with scoring server APIs, allowing instructors to access advanced scoring services through a user-friendly interface. The platform deploys a number of state-of-the-art Arabic essay scoring models with different effectiveness and efficiency figures.

Qayyem: A Real-time Platform for Scoring Proficiency of Arabic Essays

The growing demand for Mental Health (MH) services highlights the need for scalable computational tools, yet progress in computational psychology is hindered by scarce sensitive data, complex assessment procedures, and high technical barriers. While language is a well-established marker of different MH conditions, existing NLP solutions are often fragmented, closed-source, or difficult to use, limiting their adoption in interdisciplinary research.
We present TONY, an open-source, python TOolkit for NLP in clinical psYchology. TONY bridges traditional psycholinguistic analysis and modern NLP by combining interpretable lexical features with state-of-the-art lightweight transformer models within a unified and easy-to-use framework. This hybrid approach enables robust and transparent text analysis without relying on large-scale models or closed-source software.
TONY is designed for researchers and practitioners working at the intersection of NLP and MH, facilitating collaboration across disciplines. Compared to the few existing systems, TONY offers a more comprehensive and exhaustive solution, reducing the barrier to entry through a unified, modular, and reproducible pipeline that integrates classical and neural approaches in a single open framework. The toolkit is released under an open-source license and is evaluated through multiple MH–related datasets, demonstrating its flexibility and effectiveness in low-resource settings

TONY: an open-source TOolkit for Nlp in psYchology

General-purpose VLMs remain unreliable for biomedical research because valid answers in scientific papers depend on evidence split across figures, tables, charts, captions, and referring text.
Existing post-training pipelines are bottlenecked by costly expert annotation and by synthetic data that drops this evidence structure.
We present Ryze, a fully automated system that converts raw biomedical papers into an \emph{evidence-enriched} training set and a domain-specialized VLM\@.
Ryze synthesizes QA pairs with complete supporting evidence (visual element, caption, extracted structure, and referring paragraphs), reduces layout and OCR errors via chart/table-aware extraction and LLM-based cleansing, and applies a two-stage post-training strategy combining supervised fine-tuning with reinforcement learning.
Starting from Qwen3-VL-8B, Ryze produces BioVLM-8B at under \$200, achieving 48.0\% weighted accuracy on LAB-Bench---outperforming the base model by +12.6\% and surpassing GPT-5.2 by +3.8\%.
We release Ryze as open source together with the trained BioVLM-8B model.

Ryze: Evidence-Enriched Data Synthesis from Biomedical Papers

Preparing graduate students for effective professional communication remains a central goal of higher education, yet consistently assessing the quality of presentation slide decks - particularly in fast-growing AI/ML programs - poses significant challenges.
We introduce SlideGuard, an evaluation agent that assesses slide decks against a comprehensive framework of expert-defined criteria using a visual language model.
The criteria, developed in collaboration with domain experts, span visual design, narrative coherence, and argumentative structure.
SlideGuard delivers explicit, interpretable justifications for its scoring decisions, and its content-hash-based caching enables efficient re-evaluation after incremental edits, reducing the time educators spend on slide deck evaluation and accelerating feedback delivery to students.
We evaluate the approach on a dataset of 150 annotated slide decks and show that it detects the majority of expert-identified issues, with stronger results on structural and visual criteria and known limitations on subjective dimensions such as research quality.
SlideGuard is released under the Apache~2.0 license and is available on GitHub,\footnote{\url{https://github.com/Industrial-AI-Research-Lab/SlideGuard}} including all criterion prompts, configuration files, and evaluation scripts to facilitate replication.

SlideGuard: AI-Driven Evaluation of Graduate Student Presentation Materials

Interactive articles help readers engage with complex ideas through exploration, yet creating them remains costly, requiring both domain expertise and web development skills. Recent LLM-based agents can automate content creation, but naively applying them yields uncontrollable and unverifiable outputs. We present Vividoc, a human-agent collaborative system that generates interactive educational documents from a single topic input. Vividoc introduces a multi-agent pipeline (Planner, Executor, Evaluator) and the Document Specification (DocSpec), a human-readable intermediate representation that decomposes each interactive visualization into State, Render, Transition, and Constraint components. The DocSpec enables educators to review and refine generation plans before code is produced, bridging the gap between pedagogical intent and executable output. We collect a dataset of 101 real-world interactive documents across 11 domains and conduct a user study showing that ViviDoc produces documents comparable in quality to human-authored ones. Our demo is available at \url{https://vividoc.vercel.app/} and a video demonstration at \url{https://www.youtube.com/watch?v=rJrnPJLyHUI}.

Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration

With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences has become an important challenge. Current benchmarks average preferences across all users to compute aggregate ratings, overlooking individual user preferences when establishing model rankings. Since users have varying preferences in different contexts, we call for personalized LLM benchmarks that rank models according to individual needs. We compute personalized model rankings using ELO ratings and Bradley-Terry coefficients for 115 active Chatbot Arena users and analyze how user query characteristics (topics and writing style) relate to LLM ranking variations. We demonstrate that individual rankings of LLM models diverge dramatically from aggregate LLM rankings, with Bradley-Terry correlations averaging only $\rho = 0.04$ (57\% of users show near-zero or negative correlation) and ELO ratings showing moderate correlation ($\rho = 0.43$). Through topic modeling and style analysis, we find users exhibit substantial heterogeneity in topical interests and communication styles, influencing their model preferences. We further show that a compact combination of topic and style features provides a useful feature space for predicting user-specific model rankings. Our results provide strong quantitative evidence that aggregate benchmarks fail to capture individual preferences for most users, and highlight the importance of developing personalized benchmarks that rank LLM models according to individual user preferences.

Personalized Benchmarking: Evaluating LLMs by Individual Preferences

We propose a comprehensive framework for constructing multi-turn Text-to-OverpassQL dialogue datasets. Under this framework, we introduce the first multi-turn Text-to-OverpassQL dataset built upon the OverpassNL corpus. Our dataset comprises over 7,800 dialogues, each containing 2 to 4 user utterances, resulting in more than 20,000 individual utterances aligned with executable Overpass queries. To generate high-quality multi-turn dialogues, we design a four-stage pipeline. First, we convert Overpass queries into syntax trees using a custom parser developed based on the official OverpassQL grammar. This enables structural manipulation while preserving syntactic and executable validity. Second, we apply a diverse set of tree-editing templates, including both simple keyword-level changes and complex structural decompositions, to produce multiple valid and diverse Overpass queries. Third, we leverage a prompt-based approach to guide large language models in generating context-aware natural language questions, ensuring increasing inter-turn dependency across the dialogue. Finally, we implement a hybrid filtering strategy that combines manual annotation with model-assisted selection to validate alignment and correctness at scale. In addition to presenting the dataset, we evaluate the performance of several mainstream large language models and demonstrate that our end-to-end baseline model achieves competitive results. This work offers a new benchmark for studying executable semantic parsing and contextual understanding in map-based query tasks.

MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation

Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value function (critic) and reduces memory and compute overhead relative to critic-based PPO pipelines for aligning large language models. However, GRPO-style advantage estimation depends on prompt-local (within-prompt-group) reward statistics and can be unstable. In particular, when all rollouts in a prompt group receive identical rewards, the within-group reward variance becomes zero, and group normalization yields *zero* advantages for that group, impeding learning in cold-start regimes with binary verifiers. We introduce **BV-Blend**, a critic-free framework that stabilizes advantage estimation by combining prompt-local on-policy statistics with semantic-cluster-conditioned historical moments. BV-Blend maintains EMA-tracked reward moments for each cluster, derives a confidence weight from a standard error of the mean (SEM) proxy, and uses this weight to blend historical and prompt-local baseline and variance statistics into a standardized advantage for PPO-style clipped updates. Experiments on verifiable reasoning benchmarks show that BV-Blend improves training stability and performance, and remains robust in regimes where group-normalized methods may stall.

Downloads

Next from ACL 2026

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models

Similar lecture

A Rational Account of Anchor Effects in Hindsight Bias