Singapore

The low sampling efficiency during the rollout phase poses a significant challenge to scaling reinforcement learning for large language model reasoning. Existing methods attempt to improve efficiency by scheduling problems based on problem difficulties. However, these approaches suffer from unstable and biased estimations of problem difficulty and fail to capture the alignment between model competence and problem difficulty in RL training, leading to suboptimal results. To address these challenges, we introduce $\textbf{C}$ompetence-$\textbf{D}$ifficulty $\textbf{A}$lignment $\textbf{S}$ampling ($\textbf{CDAS}$). This approach allows for accurate and stable estimation of problem difficulties by aggregating historical performance discrepancies across problems. Subsequently, model competence is quantified to adaptively select problems whose difficulties align with the model&#39;s current competence using a fixed-point system. Extensive experiments in mathematical RL training show that $\textbf{CDAS}$ consistently outperforms strong baselines, achieving the highest average accuracy of 45.89\%. Furthermore, $\textbf{CDAS}$ reduces the training step time overhead by 57.06\% compared to the widely-used Dynamic Sampling strategy, verifying the efficiency of $\textbf{CDAS}$. Additional experiments on different tasks, model architectures, and model sizes demonstrate the generalization capability of $\textbf{CDAS}$.

AAAI 2026

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective

nlp: learning & optimization for nlp

nlp: (large) language models

ml: reinforcement learning

## 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.

The low sampling efficiency during the rollout phase poses a significant challenge to scaling reinforcement learning for large language model reasoning. Existing methods attempt to improve efficiency by scheduling problems based on problem difficulties. However, these approaches suffer from unstable and biased estimations of problem difficulty and fail to capture the alignment between model competence and problem difficulty in RL training, leading to suboptimal results. To address these challenges, we introduce $\textbf{C}$ompetence-$\textbf{D}$ifficulty $\textbf{A}$lignment $\textbf{S}$ampling ($\textbf{CDAS}$). This approach allows for accurate and stable estimation of problem difficulties by aggregating historical performance discrepancies across problems. Subsequently, model competence is quantified to adaptively select problems whose difficulties align with the model's current competence using a fixed-point system. Extensive experiments in mathematical RL training show that $\textbf{CDAS}$ consistently outperforms strong baselines, achieving the highest average accuracy of 45.89\%. Furthermore, $\textbf{CDAS}$ reduces the training step time overhead by 57.06\% compared to the widely-used Dynamic Sampling strategy, verifying the efficiency of $\textbf{CDAS}$. Additional experiments on different tasks, model architectures, and model sizes demonstrate the generalization capability of $\textbf{CDAS}$.

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 

Registration Required

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.

Depth-wise pruning accelerates LLM inference in resource-constrained scenarios but suffers from performance degradation due to indiscriminate removal of entire Transformer layers. This paper reveals ``Patch-Like'' redundancy across layers via correlation analysis of the outputs of different layers in reproducing kernel Hilbert space, demonstrating consecutive layers exhibit high functional similarity. Building on this observation, this paper proposes Sliding-Window Merging (SWM) - a dynamic compression method that selects consecutive layers from top to bottom using a pre-defined similarity threshold, and compacts patch-redundant layers through a parameter consolidation, thereby simplifying the model structure while maintaining its performance. Extensive experiments on LLMs with various architectures and different parameter scales show that our method outperforms existing pruning techniques in both zero-shot inference performance and retraining recovery quality after pruning. In particular, in the experiment with 35\% pruning on the Vicuna-7B model, our method achieved a 1.654\% improvement in average performance on zero-shot tasks compared to the existing method. Moreover, we further reveal the potential of combining depth pruning with width pruning to enhance the pruning effect.

Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs

The performance of egocentric AI agents is fundamentally limited by multimodal intent ambiguity. This challenge arises from a combination of underspecified language, imperfect visual data, and deictic gestures, which frequently leads to task failure. Existing monolithic Vision-Language Models (VLMs) struggle to resolve these multimodal ambiguous inputs, often failing silently or hallucinating responses. To address these ambiguities, we introduce the Plug-and-Play Clarifier, a zero-shot and modular framework that decomposes the problem into discrete, solvable sub-tasks. Specifically, our framework consists of three synergistic modules: (1) a text clarifier that uses dialogue-driven reasoning to interactively disambiguate linguistic intent, (2) a vision clarifier that delivers real-time guidance feedback, instructing users to adjust their positioning for improved capture quality, and (3) a cross-modal clarifier with grounding mechanism that robustly interprets 3D pointing gestures and identifies the specific objects users are pointing to. Extensive experiments demonstrate that our framework improves the intent clarification performance of small language models (4--8B) by approximately 30\%, making them competitive with significantly larger counterparts. We also observe consistent gains when applying our framework to these larger models. Furthermore, our vision clarifier increases corrective guidance accuracy by over 20\%, and our cross-modal clarifier improves semantic answer accuracy for referential grounding by 5\%. Overall, our method provides a plug-and-play framework that effectively resolves multimodal ambiguity and significantly enhances user experience in egocentric interaction.

Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation

Reinforcement learning (RL) has shown promise for enhancing code generation capabilities in large language models (LLMs), yet its effectiveness critically depends on high-quality test suites for reliable reward signals.
Current approaches suffer from inadequate test case quantity and quality, leading to false positives (incorrect solutions passing verification) and slow positives (valid but suboptimal implementations), which corrupt RL training dynamics.
We address these challenges through three key contributions:
(1) We systematically analyze how low-quality test suites degrade Code RL performance via reward misalignment;
(2) We propose Themis, an automated framework that transforms test case generation into code synthesis—first extracting problem constraints via template-guided parsing, then generating executable test generators through LLM-powered code synthesis, and finally validating tests through constraint-aware filtering;
(3) We develop an error-guided test case reduction method that preserves error detection efficacy while reducing test set cardinality, thereby enhancing reinforcement learning training efficiency. 
Evaluated on programming competition datasets, Themis achieves 95\% error detection rates, outperforming original test suites in most of the cases.
When integrated into RL pipelines, models trained with Themis-generated tests demonstrate consistent 3-5\% improvements across HumanEval, MBPP, and LiveCodeBench compared to the baseline, matching performance levels achieved with manually curated test suites.
Our constraint-aware test synthesis framework ensures full automation while preserving semantic validity—critical for scaling RL training to complex code generation tasks.
The framework's modular design also enables seamless integration with existing code data synthesis frameworks.

Themis: Automated Constraint-Aware Test Synthesis Framework for Code Reinforcement Learning

The illusion phenomenon of large language models (LLMs) is the core obstacle to their reliable deployment. This article formalizes the large language model as a probabilistic Turing machine by constructing a "computational necessity hierarchy", and for the first time proves the illusions are inevitable on diagonalization, incomputability, and information theory boundaries supported by the new "learner pump lemma". However, we propose two "escape routes": one is to model **Retrieval Enhanced Generations (RAGs)** as oracle machines, proving their absolute escape through "computational jumps", providing the first formal theory for the effectiveness of RAGs; The second is to formalize continuous learning as an "internalized oracle" mechanism and implement this path through a novel neural game theory framework.Finally, this article proposes a feasible new principle for artificial intelligence security - **Computational Class Alignment (CCA)**, which requires strict matching between task complexity and the actual computing power of the system, providing theoretical support for the secure application of artificial intelligence.

Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape

Aggregated time series are widely used in business and economics, where top-level sequences (e.g., category sales) aggregated from underlying sequences (e.g., individual items) often exhibit clearer trends and are therefore typically the primary focus of forecasting tasks.
However, treating top-level sequences as ordinary multivariate time series is inappropriate in the presence of coupled aggregation constraints.
The core challenge arises in coupled aggregation structures, where a single underlying sequence contributes to multiple top-level sequences, as simple nonnegativity constraints of underlying sequences induce highly complex constraints among top-level sequences.
Existing methods fail to achieve high accuracy while satisfying these constraints.
To address this, we propose ProCAST, a projection-based framework that adjusts forecasts from any multivariate base model to satisfy coupled aggregation constraints.
By introducing virtual underlying sequences and leveraging orthogonal and oblique projection, our method ensures that the top-level forecasts are feasible without explicitly deriving complex constraints.
Theoretically, we prove that the proposed method guarantees improved accuracy under distance-based loss functions.
Experiments on real-world datasets show that our method completely eliminates constraint violations while achieving higher accuracy than current state-of-the-art approaches.

ProCAST: A Projection Framework for Coupled Aggregation Constrained Multivariate Time Series Forecasting

Multimodal large language models (LMMs) have demonstrated remarkable capabilities across diverse vision-language tasks, including image captioning, visual question answering, and text-image retrieval. However, their computational complexity and memory footprint, particularly in the key-value (KV) cache during inference, pose significant challenges for real-time deployment, especially on resource-constrained devices. In this paper, we propose Dynamic KV Cache Quantization, a novel quantization strategy tailored for multimodal LMMs. Our approach applies per-channel quantization to (K) and per-token quantization to (V), leveraging their respective statistical distributions to optimize precision allocation. Additionally, we introduce an adaptive token and channel recording mechanism that dynamically adjusts quantization parameters based on real-time distribution tracking, effectively mitigating the impact of outliers. To further enhance compression efficiency, we implement fine-grained grouping, which partitions KV tensors into localized subgroups, enabling more adaptive quantization. Experimental results on LLaVA-1.5 (7B/13B) and Qwen-VL across multiple multimodal benchmarks demonstrate that our method significantly outperforms existing KV-cache quantization approaches, achieving a superior trade-off between memory efficiency and model accuracy.

Efficient Multimodal Large Language Model via Dynamic KV Cache Quantization

Recent advances in pretrained language models (PLMs) have significantly improved conversational recommender systems (CRS), enabling more fluent and context-aware interactions. To further enhance accuracy and mitigate hallucination, many methods integrate PLMs with knowledge graphs (KGs), but face key challenges: failing to fully exploit PLM reasoning over graph relationships, indiscriminately incorporating retrieved knowledge without context filtering, and neglecting collaborative preferences in multi-turn dialogues. To this end, we propose PCRS-TKA, a prompt-based framework employing retrieval-augmented generation to integrate PLMs with KGs. PCRS-TKA constructs dialogue-specific knowledge trees from KGs and serializes them into texts, enabling structure-aware reasoning while capturing rich entity semantics. Our approach selectively filters context-relevant knowledge and explicitly models collaborative preferences using specialized supervision signals. A semantic alignment module harmonizes heterogeneous inputs, reducing noise and enhancing accuracy.
Extensive experiments demonstrate that PCRS-TKA consistently outperforms all baselines in both recommendation and conversational quality.

Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language Models

To address partial node failures in unmanned aerial vehicle swarms, self-healing communication techniques are commonly employed to restore backbone connectivity while preserving area coverage. However, existing heuristic methods struggle to scale under large-scale failures and dynamic conditions, while learning-based approaches often suffer from spatial collapse, resulting in significant coverage loss. To overcome these limitations, we propose a resilient self-healing framework that enables rapid connectivity recovery and wide-area coverage through a divide-and-conquer strategy. First, we introduce a buffered dynamic virtual force expansion mechanism that categorizes pairwise distances into repulsive, neutral, and attractive zones, allowing nodes to disperse appropriately while preserving communication links and maintaining safety buffers. Subsequently, we design a multipartite graph convolution module to reason over subnetwork-level interactions and facilitate cross-subnetwork reconnection with global structural awareness. Finally, we develop an adaptive fusion strategy that combines both outputs with time-aware weighting to generate the final motion decisions. Experimental results in both random and uniform deployment scenarios demonstrate that our approach outperforms several state-of-the-art methods in terms of connectivity restoration speed and communication coverage.

Resilient UAV Swarm with Fast Connectivity Recovery and Extensive Coverage

To prevent misinformation and social issues arising from trustworthy-looking content generated by LLMs, it is crucial to develop efficient and reliable methods for identifying the source of texts. Previous approaches have demonstrated exceptional performance in detecting texts fully generated by LLMs. However, these methods struggle when confronting more advanced LLM output or text with adversarial multi task machine-revision, especially in the black-box setting, where the generating model is unknown. To address this challenge, grounded in the hypothesis that human writing possesses consistent, distinctive stylistic patterns, we propose Human Language Preference Detection (HLPD). HLPD employs a reward‐based alignment process, Human Language Preference Optimization (HLPO), to shift the scoring model’s token distribution toward human‐like writing, making the model more sensitive to human writing, therefore enhancing the identification of machine-revised text. We test HLPD in an adversarial multi‑task evaluation framework that leverages a five‑dimensional prompt generator and multiple advanced LLMs to create diverse revision scenarios. When detecting texts revised by GPT-series models, HLPD achieves a 15.11% relative improvement in AUROC over ImBD, surpassing Fast-DetectGPT by 45.56%. When evaluated in texts generated by advanced LLMs, HLPD achieves the highest average AUROC, exceeding ImBD by 5.53% and Fast-DetectGPT by 34.14%.

HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection

With the rapid growth of video data, Composed Video Retrieval (CVR) has emerged as a novel paradigm in video retrieval and is receiving increasing attention from researchers. Unlike unimodal video retrieval methods, the CVR task takes a multi-modal query consisting of a reference video and a piece of modification text as input. The modification text conveys the user's intended alterations to the reference video. Based on this input, the model aims to retrieve the most relevant target video. In the CVR task, there exists a substantial discrepancy in information density between video and text modalities. Traditional composition methods tend to bias the composed feature toward the reference video, which leads to suboptimal retrieval performance. This limitation is significant due to the presence of three core challenges: (1) modal contribution entanglement, (2) explicit optimization of composed features, and (3) retrieval uncertainty. To address these challenges, we propose the evidence-dRivEn dual-sTream diRectionAl anChor calibration networK (ReTrack). ReTrack is the first CVR framework that improves multi-modal query understanding by calibrating directional bias in composed features. It consists of three key modules: Semantic Contribution Disentanglement, Composition Geometry Calibration, and Reliable Evidence-driven Alignment. Specifically, ReTrack estimates the semantic contribution of each modality to calibrate the directional bias of the composed feature. It then uses the calibrated directional anchors to compute bidirectional evidence that drives reliable composed-to-target similarity estimation. Moreover, ReTrack exhibits strong generalization to the Composed Image Retrieval (CIR) task, achieving SOTA performance across four benchmark datasets in both CVR and CIR scenarios.

Downloads

Next from AAAI 2026

Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs

Similar lecture

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning

.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

Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs

Similar lecture

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning

Downloads