AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ACL 2026

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

Juyong Jiang, Jiasi Shen, Sunghun Kim, Kang Min Yoo, Jeonghoon Kim, Sungju Kim

While Large Language Models (LLMs) have revolutionized code generation, standard “System 1” approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative refinement strategies attempt to bridge this gap at inference time, yet they predominantly rely on external oracles, execution feedback, or computationally expensive prompt-response cycles. In this work, we propose ReflexiCoder, a novel reinforcement learning (RL) framework that internalizes the structured reasoning trajectory, encompassing initial generation, bug and optimization aware reflection, and self-correction, directly into the model’s weights. Unlike prior methods, ReflexiCoder shifts the paradigm from external-dependent refinement to an intrinsic, fully autonomous self-reflection and self-correction capabilities at inference time. We utilize an RL-only training paradigm with granular reward functions to optimize the entire reflection-correction trajectory, teaching the model how to debug without reliance on ground-truth feedback or execution engines at inference time. Extensive experiments across seven benchmarks demonstrate that our ReflexiCoder-8B establishes a new state-of-the-art (SOTA) among leading open-source models in the 1.5B-14B range, achieving 94.51% (87.20%) on HumanEval (Plus), 81.80% (78.57%) on MBPP (Plus), 35.00% on BigCodeBench, 52.21% on LiveCodeBench, and 37.34% on CodeForces in a single-attempt setting, rivaling or surpassing proprietary models like GPT-5.1. Notably, our framework is significantly more token-efficient than base models, reducing inference-time compute overhead by approximately 40% through disciplined, efficient reasoning and reflection patterns. The source code and data are available at https://github.com/juyongjiang/ReflexiCoder.

ACL 2026

MTP-RL: Acceleration of Reinforcement Learning Rollouts with Policy-Aligned Multi-Token Prediction

Ke Wang, Aohan Zeng, Zhengxiao Du, Yuxuan Hu, Bohan Zhang, Xinyi Wang, Jie Tang, Jing Zhang

Reinforcement learning (RL) is widely applied to boost the performance of pretrained models, yet its training efficiency is severely constrained by rollout generation. While speculative decoding based on multi-token prediction (MTP) offers a potential acceleration pathway, its widespread adoption is hindered by the absence of MTP in vanilla pretrained models and the rapid degradation of the MTP acceptance length in RL training. To address these issues, this paper proposes MTP-RL, a two-stage framework that pioneers effective training of MTPs in RL and accelerates the rollout phase for diverse models. It involves a pipeline to equip the multi-layer parameter-sharing MTP for all models and an innovative advantage-aware MTP optimization strategy to facilitate policy-aligned training of MTPs. Experiments demonstrate that our method not only achieves stable growth of acceptance length during RL training, but also accelerates RL rollouts, achieving an average 23.1%–55.3% reduction in rollout time compared to baselines.

ACL 2026

D2PCM:A Multi-Turn Dialogue Dataset with Personalized Contextual Memory

Zhe Yang, Yi Huang, Yaqin Chen, Chunyang Gao, Jingyu Yao, Junlan Feng

Memory serves as a pivotal component in interactive response generation, supplying essential background information and referential knowledge for dialogues. Conventional interactive algorithms have predominantly treated memory as a merely contextual element, largely neglecting the nuanced cognitive processes involved in individualized memory encoding and retrieval. This conceptual gap has led to the prevailing schema where memory-enhanced dialogue datasets incorporate monolithic, undifferentiated memory content, failing to capture the personalized nature of persoa memory processing. Grounded in the self-reference effect from cognitive psychology, we introduce a Multi-Turn Dialogue Dataset with Personalized Contextual Memory (), establishing a comprehensive benchmark to facilitate advanced research on personalized memory processing algorithms.

ACL 2026

PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models

Zetian Ouyang, Linlin Wang, Gerard De Melo, Liang He

Despite the pivotal role of numerical reasoning as the cornerstone of mathematical capabilities in large language models (LLMs) across applications, few benchmarks evaluate LLMs by integrating numerical processing and mathematical reasoning, hindering the interpretability of failures in math tasks. We introduce PyraMathBench, a comprehensive hierarchical benchmark with 27,215 questions derived from 7,404 math word problems, spanning 4 key cognitive aspects, 14 subcategories, and 2 modalities. Experiments reveal that LLMs’ performance is severely compromised by inadequate numerical computation and weak handling of abstract numerical questions. To address this, we propose the Smart Optimization Learning-based VErsatile module (SOLVE) and Interactive Relative Policy Optimization (IRPO), which enhance LLMs’ numerical-mathematical synergy via efficient tool calls (fuzzy matching and low-quality call rejection). Comparative experiments show Qwen-2.5 achieves a 5.0 score improvement with SOLVE and IRPO training.

ACL 2026

Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models

Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin, Xiang Li

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged perspective, limiting their ability to conduct deep, self-correcting reasoning over external documents, and (2) existing training paradigms rely excessively on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process. To address these issues, we propose an Reasoner-Verifier framework named Adversarial Reasoning RAG (ARR). The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other’s logic while being guided by process-aware advantage that requires no external scoring model. This reward combines explicit observational signals with internal model uncertainty to jointly optimize reasoning fidelity and verification rigor. Experiments on multiple benchmarks demonstrate the effectiveness of our method. Our code is available at link.

ACL 2026

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding

Taewon Yun, Jisu Shin, Jeonghwan Choi, Seunghwan Bang, Hwanjun Song

Distilling large reasoning models (LRMs) has become essential for making their Long-CoT reasoning capabilities practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches, which select complete reasoning traces post-hoc, overlook the collaborative potential of heterogeneous teachers and fail to adapt exploration dynamically, often leading to redundant sampling and missed opportunities for complementary reasoning. To address this, we introduce CoRD, a collaborative multi-teacher decoding framework that performs step-wise reasoning synthesis guided by predictive perplexity–based scoring and beam search. This approach enables heterogeneous LRMs to jointly construct coherent reasoning trajectories while maintaining diverse, high-potential hypotheses efficiently. Experiments show that CoRD generates higher-quality reasoning data and achieves student performance approaching teacher-level results, demonstrating that fine-grained collaboration among diverse LRMs yields structured, efficient, and robust reasoning distillation. The dataset and model are available at https://github.com/DISL-Lab/CoRD

ACL 2026

Steering LLM Thinking with Budget Guidance

Junyan Li, Wenshuo Zhao, Yang Zhang, Chuang Gan

Recent deep-thinking large language models often reason extensively to improve performance, but such lengthy reasoning is not always desirable, as it incurs excessive inference costs with disproportionate performance gains. Controlling reasoning length without sacrificing performance is therefore important, but remains challenging, especially under tight thinking budgets. We propose budget guidance, a simple yet effective method for steering the reasoning process of LLMs toward a target budget without requiring any LLM fine-tuning. Our approach introduces a lightweight predictor that models a Gamma distribution over the remaining thinking length during next-token generation. This signal is then used to guide generation in a soft, token-level manner, ensuring that the overall reasoning trace adheres to the specified thinking budget. Budget guidance enables natural control of the thinking length, along with significant token efficiency improvements over baseline methods on challenging math benchmarks. For instance, it achieves up to a 26% accuracy gain on the MATH-500 benchmark under tight budgets compared to baseline methods, while maintaining competitive accuracy with only 63% of the thinking tokens used by the full-thinking model. Budget guidance also generalizes to broader task domains and exhibits emergent capabilities, such as estimating question difficulty. We release our code and model weights at https://github.com/UMass-Embodied-AGI/BudgetGuidance.

ACL 2026

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning

Yongcan Yu, Lingxiao He, Jian Liang, Kuangpu Guo, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He

Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise.Through an empirical study, we observe that responses with medium consistency form an ambiguity region and constitute the primary source of reward noise.Crucially, we find that such spurious signals can be even amplified through group-relative advantage estimation.Motivated by these findings, we propose a unified framework, Debiased and Denoised test-time Reinforcement Learning (DDRL), to mitigate spurious signals.Concretely, DDRL first applies a frequency-based sampling strategy to exclude ambiguous samples while maintaining a balanced set of positive and negative examples.It then adopts a debiased advantage estimation with fixed advantages, removing the bias introduced by group-relative policy optimization.Finally, DDRL incorporates a consensus-based off-policy refinement stage, which leverages the rejection-sampled dataset to enable efficient and stable model updates.Experiments on three large language models across multiple mathematical reasoning benchmarks demonstrate that DDRL consistently outperforms existing TTRL baselines.The code is available at https://github.com/yuyongcan/DDRL.

ACL 2026

No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs

Wei-Chi Wu, Sheng-Lun Wei, Hen-Hsen Huang, Hsin-Hsi Chen

Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategies across ten languages of different resource levels and four benchmarks. Our analysis shows that no single strategy is universally optimal. Translation strongly benefits low-resource languages even when translation quality is imperfect, high-resource languages gain little, and prompt-based self-routing underperforms explicit translation. Motivated by these findings, we formulate prompting strategy selection as a learned decision problem and introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance. The classifiers achieve statistically significant improvements over fixed strategies across four benchmarks and generalize to unseen task formats not observed during training. Further analysis reveals that language resource level, rather than translation quality alone, determines when translation is beneficial.

ACL 2026

SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning

Fanqi Kong, Weiqin Zu, Xinyu Chen, Yaodong Yang, Song-Chun Zhu, Xue Feng

Understanding social interaction, which encompasses perceiving numerous and subtle multimodal cues, inferring unobservable mental states and relations, and dynamically predicting others’ behavior, is the foundation for achieving human-machine interaction. Despite rapid advances in Multimodal Large Language Models (MLLMs), the rich and multifaceted nature of social interaction has hindered the development of benchmarks that holistically evaluate and guide their social interaction abilities. Based on social relation theory, which has been widely regarded as a foundational framework for understanding social behavior, we provide SIV-Bench, a novel video benchmark for systematically evaluating MLLMs’ capabilities across Social Scene Understanding (SSU), Social State Reasoning (SSR), and Social Dynamics Prediction (SDP). SIV-Bench features 2,792 originally collected video clips and 5,455 meticulously generated question-answer pairs derived from a human-LLM collaborative pipeline. It covers 14 typical relationships, diverse video lengths, genres, presentation styles, and linguistic and cultural backgrounds. Our comprehensive experiments show that leading MLLMs perform relatively well on SSU but remain weak on SSR and SDP, with the systematic confusion in relation inference as a key bottleneck. An in-depth analysis of the reasoning process attributes MLLMs’ suboptimal performance to misalignment with human thoughts and insufficient reasoning depth. Moreover, we find audio and subtitles aid in reasoning-intensive SSR and SDP. Together, SIV-Bench offers a unified testbed to measure progress, expose limitations, and guide future research toward more socially intelligent MLLMs.

ACL 2026

Evaluating Large Vision Language Models on Bangla Medical Visual Question Answering

Rafid Ahmed, Intesar Tahmid, Mir Sazzat Hossain, Tasnimul Hossain Tomal, Md Mahir Jawad, Anam Borhan Uddin, Md Fahim, Md Farhad Alam Bhuiyan

Recent advancements in Large Language Models (LLMs) and Large Vision Language Models (LVLMs) have enabled general-purpose systems to demonstrate promising capabilities in complex reasoning tasks, including those in the medical domain. However, their evaluation has predominantly focused on high-resource languages, leaving low-resource contexts like Bangla underexplored. To address this gap, we introduce BanglaMedVQA, a multilingual Medical Visual Question Answering (VQA) dataset comprising clinically validated image–question–answer pairs, along with a comprehensive evaluation of current LVLMs on this resource. We rigorously evaluate nine state-of-the-art LVLMs using zero-shot, Chain-of-Thought (CoT), and LoRA fine-tuning strategies. Our results reveal a clear performance disparity: models perform well on generalized visual tasks but struggle with fine-grained diagnostic reasoning, achieving surprisingly low accuracy in specialized categories. While fine-tuning significantly improves overall accuracy, especially for Qwen2.5-VL and MedGemma 4B, limitations in specialized medical reasoning persist. Our work provides a foundation for future research in Bangla medical VQA.

ACL 2026

How to Set the Learning Rate for Large-Scale Pre-training?

Yunhua Zhou, Shuhao Xing, Junhao Huang, Xipeng Qiu, Qipeng Guo

Optimal configuration of the learning rate (LR) is a fundamental yet formidable challenge in large-scale pre-training. Given the stringent trade-off between training costs and model performance, the pivotal question is whether the optimal LR can be accurately extrapolated from low-cost experiments. In this paper, we formalize this investigation into two distinct research paradigms: Fitting and Transfer. Within the Fitting Paradigm, we innovatively introduce a Scaling Law for search factor, effectively reducing the search complexity from \mathcal{O}(n^3) to \mathcal{O}(n \cdot C_{D} \cdot C_{\eta}) via predictive modeling. Within the Transfer Paradigm, we extend the principles of \muTransfer to the Mixture of Experts (MoE) architecture, broadening its applicability to encompass model depth, weight decay, and token horizons.By pushing the boundaries of existing hyperparameter research in terms of scale, we conduct a comprehensive comparison between these two paradigms. Our empirical results challenge the scalability of the widely adopted \muTransfer in large-scale pre-training scenarios. Furthermore, we provide a rigorous analysis through the dual lenses of training stability and feature learning to elucidate the underlying reasons why module-wise parameter tuning underperforms in large-scale settings. This work offers systematic practical guidelines and a fresh theoretical perspective for optimizing industrial-level pre-training.

ACL 2026

DANCE: Diversity-attended Dynamic Caching with Asymmetric Quantization for Test-time Adaptation of Vision-Language Models

Shunge Zou, Changhu Wang, Wei Ju, Ziyue Qiao, Xiao Luo

This paper studies the problem of test-time adaptation for vision-language models (VLMs). Recent approaches typically measure the prediction entropy to store a confident cache for logit refinement. However, these confident samples tend to approach prototypes with limited coverage of data distribution, which could result in biased predictions as the distribution evolves. Towards this end, we propose a novel approach named Diversity-attended Dynamic Caching with Asymmetric Quantization (DANCE) for test-time adaptation of VLMs. The core of our DANCE is to maintain a dynamic cache to store diversity-aware test samples, which support efficient logit adjustment via asymmetric quantization. In particular, we first generate multiple augmented views of each sample and aggregate their outputs from pre-trained VLMs via a consistency-aware mechanism. More importantly, we construct a dynamic cache, which stores the most reliable and diverse samples to cover evolving test distributions. To measure the diversity efficiently, we quantize cached samples and compute the asymmetric similarity across query samples and memory samples, which guide the cache updating via replacing samples with the lowest scores iteratively. Finally, we leverage the asymmetric similarity between the quantized prototype representations from the dynamic cache to update logits under distribution shifts. Extensive experiments on various benchmark datasets validate the superiority of the proposed DANCE in different settings.

ACL 2026

Interpretability from the Ground Up: Stakeholder-Centric Design of Automated Scoring in Educational Assessments

Yunsung Kim, Michael Hardy, Joseph Tey, Candace Thille, Christopher J Piech

AI-driven automated scoring systems offer scalable and efficient means of evaluating complex student-generated responses. Yet, despite increasing demand for transparency and interpretability, the field has yet to develop a widely accepted solution for interpretable automated scoring to be used in large-scale real-world assessments. This work takes a principled approach to address this challenge. We analyze the needs and potential benefits of interpretable automated scoring for various assessment stakeholder groups and develop four principles of interpretability – (F)aithfulness, (G)roundedness, (T)raceability, and (I)nterchangeability (FGTI) – targeted at those needs. To illustrate the feasibility of implementing these principles, we develop the AnalyticScore framework as a baseline reference framework. When applied to the domain of text-based constructed-response scoring, AnalyticScore outperforms many uninterpretable scoring methods in terms of scoring accuracy and is, on average, within 0.06 QWK of the uninterpretable SOTA across 10 items from the ASAP-SAS dataset. By comparing against human annotators conducting the same featurization task, we further demonstrate that the featurization behavior of AnalyticScore aligns well with that of humans.

ACL 2026

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment

Ziyang Chen, Zhenxuan Huang, Yile Wang, Weiqin Wang, Lu Yin, Hui Huang

Traditional sentence embedding methods employ token-level contrastive learning on non-generative pre-trained models. Recently, there have emerged embedding methods based on generative large language models (LLMs). These methods either rely on fixed prompt templates or involve modifications to the model architecture. The former lacks further optimization of the model and results in limited performance, while the latter alters the internal computational mechanisms of the model, thereby compromising its generative capabilities. We propose SemPA, a novel approach that boosts the sentence representations while preserving the generative ability of LLMs via semantic preference alignment. We leverage sentence-level Direct Preference Optimization (DPO) to efficiently optimize LLMs on a paraphrase generation task, where the model learns to discriminate semantically equivalent sentences while preserving inherent generative capacity. Theoretically, we establish a formal connection between DPO and contrastive learning under the Plackett-Luce model framework. Empirically, experimental results on both semantic textual similarity tasks and various benchmarks for LLMs show that SemPA achieves better semantic representations without sacrificing the inherent generation capability of LLMs.

ACL 2026

Adaptive Backtracking for Privacy Protection in Large Language Models

Zhihao Yao, Yuxuan Gu, Xiachong Feng, Weitao Ma, Bo Li, Xiaocheng Feng, Bing Qin

The privacy leakage problem has become a critical topic in large language models, especially in the scenario of retrieval augmented generation.Current defense methods mitigate privacy leakage but are still suffering from the trade-off between privacy protection and response availability.To address the problem, we propose to explicitly capture the latent leakage tendency of LLM during the generation process, which is able to protect privacy from a more fundamental perspective.In detail, we propose ABack, a training-free mechanism that synchronously monitors the decoding steps, derives the initial leakage intention via modeling mental states, and rewrites the response with privacy awareness. In addition, we construct a new benchmark especially for personally identifiable information, considering the lack of formal privacy datasets.Experiments show that ABack improves privacy by up to 14% over strong baselines against adversarial attacks, avoiding the degradation of response utility.

ACL 2026

Enhancing Multilingual Reasoning via Steerable Model Merging

Zhuoran Li, Rui Xu, Jian Yang, Junnan Liu, Zhijun Chen, Qianren Mao, Hongcheng Guo, Jiaheng Liu, Likang Xiao, Ming Li, Xiaojie Wang

Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model. It has achieved promising generalization in multilingual reasoning tasks by aligning feature spaces of different models. However, the merged single model often fails to address the conflicts between source models, leading to suboptimal performance. In other words, the one-size-fits-all merging strategy may not align with the characteristics of different inputs which may require prioritizing certain models over others. To this end, we propose a Steerable Model Merging (ST-Merge) framework to modulate the contribution of each source model. To realize this idea, we introduce a gated cross-attention mechanism to weight or filter the two attended source models in an adaptive manner. Extensive experiments demonstrate that ST-Merge consistently outperforms multiple strong baselines on four multilingual reasoning benchmarks across 21 different languages.

ACL 2026

Synergizing Stylometrics with Semantics: Dual-Path Framework for LLM Detection and Attribution

Xingyu Lu, Yumeng Ma, Xiang Zhou, Shengli Gan, Guiying Deng, Yang Wen, Yanbing Liu

The widespread application of LLMs has made MGT detection increasingly important in cyberspace security and governance. The existing detection paradigms mainly focus on statistical likelihood or deep embeddings. However, in complex applications such as short texts, derivative works, and cross-domain content, the discriminative capabilities fragility of these conventional methods increases significantly with the development of LLMs. Conversely, our research reveals that LLMs exhibit inherent style inertia. To address these limitations, this study attempts to synergize stylometrics and semantics for identifying MGT. This approach draws from the forensic perspective of experts who detect human imitation by focusing on stylistic nuances. Based on the above inspiration, we propose Stylometric-Semantic LLM Attribution (SSLA), a framework that extracts model-specific stylistic fingerprints across lexical, syntactic, and structural dimensions. SSLA employs a dual-path attention fusion architecture to dynamically integrate explicit stylistic signals with implicit semantic encodings. Extensive experiments across six LLM families demonstrate that our method achieves state-of-the-art performance. Notably, SSLA achieves a Macro-F1 score of 95.6% on the challenging Wikipedia dataset, demonstrating exceptional robustness and surpassing state-of-the-art baselines like OTBDetector.

ACL 2026

♪ Something Just Like TRuST ♪ *: Toxicity Recognition of Span and Target

Berk Atıl, Namrata Sureddy, Rebecca J. Passonneau

Toxic language includes content that is offensive, abusive, or that promotes harm. Progress in preventing toxic output from large language models (LLMs) is hampered by inconsistent definitions of toxicity. We introduce TRuST, a large-scale dataset that unifies and expands prior resources through a carefully synthesized definition of toxicity, and corresponding annotation scheme. It consists of ∼300k annotations, with high-quality human annotation on ∼11k. To ensure high-quality, we designed a rigorous, multi-stage human annotation process, and evaluated the diversity of the annotators. Then we benchmarked state-of-the-art LLMs and pre-trained models on three tasks: toxicity detection, identification of the target group, and of toxic words. Our results indicate that fine-tuned PLMs outperform LLMs on the three tasks, and that current reasoning models do not reliably improve performance. TRuST constitutes one of the most comprehensive resources for evaluating and mitigating LLM toxicity, and other research in socially-aware and safer language technologies.

ACL 2026

Towards Unified Multimodal Large Language Models: A survey

Xu Ma, Yitian Zhang, Yun Fu

The recent surge of interest in unified Multimodal Large Language Models (MLLMs) has catalyzed rapid progress toward general-purpose generation and understanding across different modalities. Despite the remarkable advancements, the field lacks a systematic and cohesive framework that connects these developments, revisits the motivations, and situates current trends within a broader landscape. In this survey, we present a comprehensive and in-depth review of unified MLLMs, offering both a methodology taxonomy and unique perspectives on the field. We begin by outlining the foundational concepts and prerequisites for understanding unified MLLMs. We then delve into designs from different aspects, including model architectures, loss functions, alignment techniques, and different representation strategies. Furthermore, we discuss persistent challenges and identify promising directions for future research. By bridging scattered progress and providing a consolidated view, this survey aims to foster a deeper and systematical understanding of unified MLLMs and inspire future innovations in building truly general multimodal intelligence.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.