Singapore

Large reasoning models (LRMs) have recently achieved significant progress in complex reasoning tasks, aided by reinforcement learning with verifiable rewards. However, LRMs often suffer from overthinking, expending excessive computation on simple problems and reducing efficiency. Existing efficient reasoning methods typically require accurate task assessment to preset token budgets or select reasoning modes, which limits their flexibility and reliability. In this work, we revisit the essence of overthinking and identify that encouraging effective steps while penalizing ineffective ones is key to its solution. To this end, we propose a novel rule-based verifiable stepwise reward mechanism (VSRM), which assigns rewards based on the performance of intermediate states in the reasoning trajectory. This approach is intuitive and naturally fits the step-by-step nature of reasoning tasks. We conduct extensive experiments on standard mathematical reasoning benchmarks, including AIME24 and AIME25, by integrating VSRM with PPO and Reinforce++. Results show that our method achieves substantial output length reduction while maintaining original reasoning performance, striking an optimal balance between efficiency and accuracy. Further analysis of overthinking frequency and pass@k score before and after training demonstrates that our approach indeed effectively suppresses ineffective steps and encourages effective reasoning, fundamentally alleviating the overthinking problem.

AAAI 2026

Promoting Efficient Reasoning with Verifiable Stepwise Reward

reinforcement learning with verifiable rewards

large reasoning models

efficient reasoning

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

ACL 2026

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

poster

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

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 AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Due to privacy concerns, open dialogue datasets for mental health are primarily generated through human or AI synthesis methods. However, the inherent implicit nature of psychological processes, particularly those of clients, poses challenges to the authenticity and diversity of synthetic data. In this paper, we propose ECAs (short for Embodied Conversational Agents), a framework for embodied agent simulation based on Large Language Models (LLMs) that incorporates multiple psychological theoretical principles. Using simulation, we expand real counseling case data into a nuanced embodied cognitive memory space and generate dialogue data based on high-frequency counseling questions. We validated our framework using the D$^4$ dataset. First, we created a public ECAs dataset through batch simulations based on D$^4$. Licensed counselors evaluated our method, demonstrating that it significantly outperforms baselines in simulation authenticity and necessity. Additionally, two LLM-based automated evaluation methods were employed to confirm the higher quality of the generated dialogues compared to the baselines.

An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling

Understanding human emotions from an image is a challenging yet essential task for vision-language models. While recent efforts have fine-tuned vision-language models to enhance emotional awareness, most approaches rely on global visual representations and fail to capture the nuanced, multi-faceted nature of emotional cues. Furthermore, most existing approaches adopt instruction tuning, which requires costly dataset construction and involves training a large number of parameters, thereby limiting scalability and efficiency. To address these challenges, we propose MASP, a novel framework for Multi-Aspect guided emotion reasoning with Soft Prompt tuning in vision-language models. MASP explicitly separates emotion-relevant visual cues via multi-aspect cross-attention modules and guides the language model using soft prompts, enabling efficient and scalable task adaptation without modifying the base model. Our method achieves state-of-the-art performance on various emotion recognition benchmarks, demonstrating that explicit modeling of multi-aspect emotional cues with soft prompt tuning leads to more accurate and interpretable emotion reasoning in vision-language models.

MASP: Multi-Aspect Guided Emotion Reasoning with Soft Prompt Tuning In Vision-Language Models

Centralized training with decentralized execution (CTDE) is a framework for MARL with wide applications.
In CTDE, agents leverage global state information during training to mitigate the non-stationarity of the MARL environment, but rely solely on partial observations during execution. 
Recent work has highlighted the growing importance of inter-agent communication for more effective learning and coordination. 
However, most existing methods overlook the fact that real-world communication channels are often bandwidth-constrained and imperfectly reliable.
Toward more communication-efficient and robust MARL, we extend the conventional CTDE framework with an information hub.
The hub collects local observations from the agents to restore the global states, which are then delivered to the agents on demand.
To this end, technical mechanisms are designed to enable effective global reconstruction with incomplete observations, as well as agent-specific attention to the reconstructed global information.
Experiments on multiple cooperative MARL benchmarks demonstrate that our method achieves state-of-the-art performance compared to popular MARL algorithms while substantially reducing communication overhead and exhibiting strong robustness under imperfect communication channels.

Communication-efficient Multi-Agent Reinforcement Learning with Spatiotemporal Information Hub

We study online interval scheduling in the irrevocable setting, where each interval must be immediately accepted or rejected upon arrival. The objective is to maximize the total length of accepted intervals while ensuring that no two accepted intervals overlap. We consider this problem in a learning-augmented setting, where the algorithm has access to (machine-learned) predictions. The goal is to design algorithms that leverage these predictions to improve performance while maintaining robust guarantees in the presence of prediction errors.

Our main contribution is the SemiTrust-and-Switch framework, which provides a unified approach for combining prediction-based and classical interval scheduling algorithms. This framework applies to both deterministic and randomized algorithms and captures the trade-off between consistency (performance under accurate predictions) and robustness (performance under adversarial inputs). Moreover, we provide lower bounds, proving the tightness of this framework in particular settings.

We further design a randomized algorithm that smoothly interpolates between prediction-based and robust algorithms. This algorithm achieves both robustness and smoothness—its performance degrades gracefully with the quality of the prediction.

A Switching Framework for Online Interval Scheduling with Predictions

We study planning in a fragment of PDDL with qualitative state-trajectory constraints, capturing safety requirements, task ordering conditions, and intermediate sub-goals commonly found in real-world problems. A prominent approach to tackle such problems is to compile their constraints away, leading to a problem that is supported by state-of-the-art planners. Unfortunately, existing compilers do not scale on problems with a large number of objects and high-arity actions, as they necessitate grounding the problem before compilation. To address this issue, we propose two methods for compiling away constraints without grounding, making them suitable for large-scale planning problems. We prove the correctness of our compilers and outline their worst-case time complexity. Moreover, we present a reproducible empirical evaluation on the domains used in the latest International Planning Competition. Our results demonstrate that our methods are efficient and produce planning specifications that are orders of magnitude more succinct than the ones produced by compilers that ground the domain, while remaining competitive when used for planning with a state-of-the-art planner.

Two Constraint Compilation Methods for Lifted Planning

Dysarthric speech reconstruction (DSR) aims to enhance the intelligibility of dysarthric speech. Compared with normal speech, the dysarthric speech is characterized by its pathological features, including discontinuous pronunciation, slow speech, hoarseness, and improper pauses. Significant disparities in the feature space between normal and dysarthric speech may result in suboptimal speech reconstruction, thereby degrading speech intelligibility. To enhance the reconstruction ability of speech feature spaces, this paper proposes a DSR model named the Encoding-Aligned Variational Autoencoder (EA-VAE). By incorporating alignment modules of frame-level embedding features, prior distributions, and duration into the encoder of the VAE, the model explicitly aligns the dysarthric speech encoding with a representation of the parallel normal speech. A shared decoder is then used to generate speech with improved intelligibility. Experimental results on the UASpeech benchmark confirm that EA-VAE achieves state-of-the-art performance, with a 31.7% relative word error rate reduction and the highest subjective MOS score (4.48), thoroughly validating the effectiveness and advancements of the proposed method in dysarthric speech reconstruction.

EA-VAE: Learning to Reconstruct Dysarthric Speech via Variational Autoencoder with Encoding Alignment

Data-Centric Sequential Recommendation (DaCSR) has emerged as a promising technique that enhances dataset quality to better capture user preferences without increasing training complexity. However, mining item relations to improve data quality remains challenging due to the intricate nature of interaction sequences. Existing methods predominantly either: 1) optimize models to learn such item relations from fixed datasets at significant training cost, or 2) employ generative models to adaptively learn only interaction patterns, which lack interpretability and cannot guarantee effective data quality enhancement. In this paper, we pioneer a relation-guided dataset augmentation and regeneration framework for sequential recommendation called \textbf{RaSR}. This framework can significantly improve model performance on original datasets while maintaining training efficiency without modifying the model architecture. Specifically, we first preprocess user interactions to construct standardized sequential data and extract semantic representations via a Large Language Model (LLM). We then build a multi-relation graph with manually predefined metrics and semantic representations to generate augmented datasets. Finally, a relation-aware generator can produce regenerated datasets with both the multi-relation graph and the augmented dataset. To verify the effectiveness of RaSR, we conduct experiments on various backbone models and datasets, and achieve significant performance improvement compared to training the model only on the original dataset. The anonymous code is available at: \url{https://anonymous.4open.science/r/RaSR}.

Data-Centric Sequential Recommendation with Relation-Augmented Generation

Electroencephalography (EEG) plays a vital role in clinical and cognitive applications such as epilepsy diagnosis and emotion recognition. However, the low signal-to-noise ratio, inter-subject variability, and inherent non-stationarity of EEG signals present substantial modeling challenges. While recent Transformer-based models offer promising long-range modeling capabilities, their self-attention mechanism behaves as a low-pass filter, suppressing high-frequency neural patterns critical for decoding transient events. In this work, we provide the first formal analysis demonstrating this low-pass behavior in self-attention mechanisms when applied to EEG signals, revealing a fundamental limitation of deep attention-based EEG models. To address this, we propose SEBSFormer, a spectral-enhanced bi-Stream Transformer that jointly models temporal dependencies and spectral structures. SEBSFormer integrates three key modules: a spectral compensation module that restores high-frequency components via residual correction in the Fourier domain; a multi-scale temporal attention module for saliency-guided temporal compression; and a graph-guided dynamic fusion module for adaptive spatial aggregation across electrodes. Extensive experiments on three benchmark datasets—TUAB, TUEV, and SEED—demonstrate that SEBSFormer consistently outperforms existing state-of-the-art models across both clinical and affective tasks. Our findings establish a new paradigm for frequency-aware EEG modeling.

SEBSFormer: A Spectral-Enhanced Bi-Stream Transformer for Robust EEG Decoding

The maximally diverse grouping problem (MDGP) seeks to partition the vertices of a complete graph into a fixed number of groups under capacity constraints, maximizing the sum of edge weights within each group. MDGP is an NP-hard combinatorial optimization problem and has wide real-world applications. In this paper, we propose an adaptive configuration-aware simulated annealing (ACSA) algorithm to solve MDGP. First, ACSA adopts a relaxation-based insertion strategy, which temporarily relaxes capacity constraints to expand the neighborhood and allow effective exploration of promising regions. Second, a memory-based swap mechanism is introduced to integrate high-potential suboptimal swap moves into the conventional best-swap operation, thereby achieving a better balance between diversification and intensification of the search. Finally, ACSA employs a vertex-wise sequential coordination strategy to dynamically organize the insertion and swap moves, which enhances the search flexibility. Experiments on 500 benchmark instances demonstrate the strong competitiveness of ACSA, as it improves the best results among the state-of-the-art algorithms on 460 instances and matches them on 39 instances.

An Adaptive Configuration-Aware Simulated Annealing for the Maximally Diverse Grouping Problem

We present a class of stochastic interventions for causal inference with discrete treatments defined through the marginals of the solution to a cost-penalized Kullback–Leibler projection problem. This formulation seeks a stochastic plan that minimizes the expected cost of reallocating treatments while penalizing the divergence from the independent product of the organic propensity scores and a prespecified target distribution. This problem arises as a limiting case of a relaxed optimal transport problem without marginal constraints. The resulting source marginal yields a generalization of incremental propensity score interventions (IPIs), accommodating arbitrary target distributions and cost structures. Like classical IPIs, these interventions are governed by a tunable parameter and do not require the positivity assumption for identification. We derive the influence functions for the corresponding expected outcomes and develop semiparametric estimators that remain robust under model misspecification, as demonstrated in a simulation study. We illustrate the practical utility of these methods by analyzing policies for ADHD treatment and their impact on children’s academic achievement.

Downloads

Next from AAAI 2026

An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling

Similar lecture

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling

Similar lecture

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models

Downloads