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

PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints

Minjun Park, Donghyun Kim, Hyeonjong Ju, Seungwon Lim, Dongwook Choi, Taeyoon Kwon, Minju Kim, Jinyoung Yeo

We are entering an era in which individuals and organizations increasingly deploy dedicated AI agents that interact and collaborate with other agents.However, the dynamics of multi-agent collaboration under privacy constraints remain poorly understood.In this work, we present PAC\text{-}Bench, a benchmark for systematic evaluation of multi-agent collaboration under privacy constraints.Experiments on PAC\text{-}Bench show that privacy constraints substantially degrade collaboration performance and make outcomes depend more on the initiating agent than the partner.Further analysis reveals that this degradation is driven by recurring coordination breakdowns, including early-stage privacy violations, overly conservative abstraction, and privacy-induced hallucinations.Together, our findings identify privacy-aware multi-agent collaboration as a distinct and unresolved challenge that requires new coordination mechanisms beyond existing agent capabilities.

ACL 2026

Synergizing Semantic Anchors and Ordinal Smoothed Cross-Entropy for Speech Fluency Classification

Mulati Kahaer, Sirajahmat Ruzmamat, XuDong Pang, Subinuer Maimaitituerxun, Zaokere Kadeer, Abudurexiti Reheman, Wenwen Lu, Panpan Zheng, Aishan Wumaier

Speech fluency is a core indicator of second language proficiency and a critical component of Computer-Assisted Pronunciation Training (CAPT) systems. Accurate assessment requires models to perceive both macroscopic speech flow trends and microscopic local anomalies. However, existing methods struggle to bridge the semantic gap between static expert priors and dynamic temporal representations, while often overlooking the inherent ordinal nature of fluency scores. To address these challenges, we first construct a set of expert features targeting fluency disruptions and rhythmic regularity to provide explicit linguistic priors. Building on this, we propose the Multimodal Multi-Stream Fusion Classification (MMSFC) network. It employs a Mutual Cross-Attention (MCA) mechanism that leverages these expert features as “semantic anchors” to actively guide Whisper’s temporal representations and integrate decoder contexts, achieving deep interaction between global priors and local dynamics. Furthermore, we propose the Ordinal Smoothed Cross-Entropy (OSCE) loss. By constructing distance-aware soft target distributions coupled with confidence-adaptive smoothing and boundary enhancement, OSCE explicitly models ordinal relationships to resolve boundary ambiguity. Experiments on SpeechOcean762 show MMSFC achieves 83.40% accuracy, significantly outperforming strong baselines. Notably, OSCE also demonstrates superior generalization potential in cross-domain CV and NLP tasks. Our code is available at https://github.com/speech26ai/MMSFCCode.

ACL 2026

MA^{2}P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion

Dingyi Zhang, Ziqing Zhuang, Linhai Zhang, Ziyang Gao, Deyu Zhou

Persuasive dialogue generation plays a vital role in decision-making, negotiation, counseling, and behavior change, yet it remains a challenging problem. In complex persuasion where the persuadee’s internal states are not expressed clearly, the persuader must interpret responses, infer the persuadee’s latent mental states (e.g., beliefs and desires), and translate them into targeted, strategy-consistent actions; however, current approaches often produce generic or weakly grounded responses even when such cues are identified. Moreover, although large language models (LLMs) can generate persuasive content, their performance varies substantially across domains due to uneven knowledge coverage and limited reasoning generalization. To address these challenges, we propose MA^{2}P, a meta-cognitive autonomous intelligent agent framework for complex persuasion. Specifically, we develop an autonomous multi-agent architecture that coordinates perception management, mental-state inference, strategy execution, memory maintenance, and performance evaluation. To mitigate cross-domain performance variation, we further design a meta-cognitive configurator that selects an appropriate meta-strategy from a structured knowledge base at the outset, thereby guiding subsequent reasoning and planning. Experimental results show that our approach achieves a higher persuasion success rate than baselines.

ACL 2026

Explainable Quantum Program Repair with Verifiable Proof Traces

Tingting Li, Ziming Zhao, Zhaoxuan Li, Jiongchi Yu, Xiaofei Yue, Jianwei Yin

Large language models have recently advanced automated program repair, yet most existing approaches provide only post-hoc natural-language explanations that are neither executable nor verifiable. This limitation is especially critical for quantum programs, where correctness hinges on subtle semantic properties such as circuit equivalence and fidelity preservation. We propose Explainable Quantum Program Repair, a framework that couples repair generation with machine-checkable executable explanations. Given a buggy quantum circuit, a language model proposes candidate repairs together with structured transformation rationales, which are compiled into proof traces and validated using formal verification backends, including circuit equivalence checking, ZX-calculus reasoning, stabilizer analysis, and quantum simulation. Only repairs whose explanations are fully verified are accepted. Experiments on QASMBench with mutation-generated quantum program bugs demonstrate that our approach achieves competitive repair success while substantially improving semantic precision and explanation faithfulness over baselines that rely on unconstrained or purely natural-language explanations.

ACL 2026

Prompting the Unknown: Understanding Response Uncertainty in Large Language Models

Ze-Yu Zhang, Arun Verma, Finale Doshi-Velez, Bryan Kian Hsiang Low

Large language models (LLMs) are widely used in decision-making across diverse domains. Ensuring the generation of safe and reliable responses is critical for the effective deployment of LLM-based applications, particularly in high-stakes domains such as healthcare and finance. Most of these applications typically use carefully crafted prompts to guide response generation; however, the relationship between prompts and the reliability of LLM-generated responses is not yet fully understood. To address this gap, we propose a novel prompt-response concept model that explains the relationship between the amount of task-relevant information (informativeness) provided in the prompt and the LLM-generated response uncertainty by identifying four sources of response uncertainty: prompt underspecification, model quality, task variability, and semantic redundancy. We prove that response uncertainty decreases as prompt informativeness or model quality increases, mirroring the behavior of epistemic uncertainty in probabilistic models. Our experimental results on real-world datasets further validate our proposed model and corroborate the theoretical results.

ACL 2026

Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions

Jiseon Kim, Jea Kwon, Luiz Felipe Vecchietti, Wenchao Dong, Jaehong Kim, Meeyoung Cha

Human moral judgment is context-dependent and changes based on interpersonal relationships. As large language models (LLMs) increasingly serve as decision-support systems, it is critical to understand if they encode these social nuances. We characterize LLM behavior using the Whistleblower’s Dilemma, systematically varying two experimental factors: crime severity and relational closeness. Our study compares three evaluative perspectives: (1) moral rightness (general prescriptive norms), (2) predictive human behavior (how models expect people to navigate social situations), and (3) models’ own decision-making. By analyzing the reasoning processes, we find a clear cross-perspective divergence: moral rightness remains consistently fairness-oriented, while predicted human behavior shifts with relational context toward loyalty. Crucially, the model decisions mirror moral rightness judgments, rather than their behavioral predictions. This cross-perspective inconsistency suggests that LLM decision-making favors abstract rules over the social sensitivity found in their internal modeling, potentially producing conflicting expectations in real-world deployments.

ACL 2026

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

Zihan Wang, Lam Nguyen, Zhengyang Zhao, Mengyue Yang, Chengwei Qin, Yujiu Yang, Linyi Yang

The saturation of high-quality pre-training data has shifted research focus toward evolutionary systems capable of continuously generating novel artifacts, leading to the success of AlphaEvolve. However, the progress of such systems is hindered by the lack of rigorous, quantitative evaluation. To tackle this challenge, we introduce CreativeBench, a benchmark for evaluating machine creativity in code generation, grounded in a classical cognitive framework. Comprising two subsets – CreativeBench-Combo and CreativeBench-Explore – the benchmark targets combinatorial and exploratory creativity through an automated pipeline utilizing reverse engineering and self-play. By leveraging executable code, CreativeBench objectively distinguishes creativity from hallucination via a unified metric defined as the product of quality and novelty. Our analysis of state-of-the-art models reveals distinct behaviors: (1) scaling significantly improves combinatorial creativity but yields diminishing returns for exploration; (2) larger models exhibit “convergence-by-scaling,” becoming more correct but less divergent; and (3) reasoning capabilities primarily benefit constrained exploration rather than combination. Finally, we propose EvoRePE, a plug-and-play inference-time steering strategy that internalizes evolutionary search patterns to consistently enhance machine creativity.

ACL 2026

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, dongsheng wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from “overthinking”, producing excessively long reasoning traces that increase latency and memory usage. Existing LRMs typically enforce conciseness with uniform length penalties, which over-compress crucial early deduction steps at the sequence level and indiscriminately penalize all queries at the group level. To solve these limitations, we propose PACE, a dual-level framework for prefix-protected and difficulty-aware compression under hierarchical supervision. At the sequence level, prefix-protected optimization employs decaying mixed rollouts to maintain valid reasoning paths while promoting conciseness. At the group level, difficulty-aware penalty dynamically scales length constraints based on query complexity, maintaining exploration for harder questions while curbing redundancy on easier ones. Extensive experiments on DeepSeek-R1-Distill-Qwen (1.5B/7B) demonstrate that PACE achieves a substantial reduction in token usage (up to 55.7%) while simultaneously improving accuracy (up to 4.1%) on math benchmarks, with generalization ability to code, science, and general domains.

ACL 2026

VET: Verifiable Execution Tracing for Reliable Text-to-SQL Generation

Dongyu Wang, Jingyu Li, Lan Zhang, Ganggang Yu, Liang Huang

Large language models (LLMs) have shown remarkable capabilities in text-to-SQL generation, yet existing approaches remain prone to hallucinations and lack verification mechanisms. Current methods such as Chain-of-Thought (CoT) and Program-of-Thought (PoT) typically rely on intermediate reasoning that is either purely textual or executed only as a final step, leaving the reasoning process opaque and prone to grounding and logical hallucinations. In this paper, we introduce Verifiable Execution Tracing (VET), a novel reasoning paradigm that transforms text-to-SQL from unverifiable textual rationales into step-wise executable semantics. VET addresses these limitations by constraining the reasoning process within a candidate schema space and formulating it as a sequence of executable Python steps. Crucially, each step is executed against the real database to produce observable intermediate results, which serve as immediate verification feedback and transform the traditionally opaque generation process into a transparent, debuggable interaction with database reality.Experiments show consistent gains under matched, training-free settings, achieving 70.93% execution accuracy on BIRD and 37.04% on Spider 2.0-lite, with particularly strong improvements on complex queries.

ACL 2026

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus

Yexing Du, kaiyuan liu, Bihe Zhang, Youcheng Pan, Bo Yang, Liangyu Huo, Xiyuan Zhang, Jian Xie, Daojing He, Yang Xiang, Ming Liu, Bing Qin

With the rapid advancement of Multimodal Large Language Models (MLLMs), their potential has gained significant attention in Chinese Classical Studies (CCS). While existing research primarily focuses on text and visual modalities, the audio corpus within this domain remains largely underexplored. To bridge this gap, we introduce the Multi-task Classical Chinese Literary Genre Audio Corpus (MCGA), a 119-hour corpus comprising 22,000 audio samples. It encompasses a diverse range of literary genres across six tasks: Automatic Speech Recognition (ASR), Speech-to-Text Translation (S2TT), Speech Emotion Captioning (SEC), Spoken Question Answering (SQA), Speech Understanding (SU), and Speech Reasoning (SR). Through the evaluation of ten MLLMs, our experimental results demonstrate that current MLLMs still face substantial challenges on the MCGA test set. Furthermore, we introduce a domain-specific metric for SEC and a metric to measure the consistency between speech and text capabilities. We release MCGA to the public to facilitate the development of more robust MLLMs. MCGA Corpus: https://github.com/yxduir/MCGA

ACL 2026

Safety Sidecar: Reflection-Driven Runtime Control for Safer Agents

Wang Bin, Quan Jiazheng, Xingrui Yu, Hu Hansen, YU HAO, Anjun Gao, Zhenglin Wan, Hui Li, Ivor Tsang

Autonomous LLM agents are increasingly deployed in complex environments as tool-using systems. However, their safety remains fragile, as minor reasoning or retrieval errors can be amplified into hazardous actions within the agentic workflow. Existing defenses, often limited to static prompts or post-hoc guardrails, fail to provide runtime intervention or cross-architecture portability. In this paper, we propose Safety Sidecar, a model-agnostic, plug-and-play module designed to provide standardized runtime safety control and auditability for arbitrary agent workflows. Safety Sidecar operationalizes reflection as a closed-loop controller: it dynamically monitors decision traces, retrieves evidence-based repair exemplars from a reflective memory, and enforces risk-mitigating revisions before execution. Crucially, it employs external verifiers to gate both action release and memory updates, producing a transparent, auditable trail of retrieved evidence and applied constraints.We instantiate and systematically evaluate Safety Sidecar in secure code generation—a high-stakes domain with objective vulnerability signals. Experimental results across eight CWE scenarios and four representative LLMs demonstrate that Safety Sidecar consistently improves the secure-solution rate by 2.9–11.2 percentage points while maintaining competitive functional correctness. Efficiency analysis shows the framework is practical for deployment, with reflection adding only 3.2s to end-to-end latency and a negligible average cost of 5.37 \times 10^{-4} per scenario. Our findings position Safety Sidecar as a portable and efficient control layer for enhancing the safety, compliance, and auditability of LLM-based agents.

ACL 2026

ReFreeKV: Towards Threshold-Free KV Cache Compression

Xuanfan Ni, Liyan Xu, Chenyang Lyu, Longyue Wang, Mo Yu, lemao liu, Fandong Meng, Jie Zhou, Piji Li

To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning.While these techniques can accomplish lossless memory reduction on many datasets, they often hinge on an under-emphasized condition: an input/domain-specific threshold for KV cache budget needs to be pre-determined to achieve the optimal performance.However, such input-sensitive design may be considerably limited in real-world scenarios, as open-domain inputs span diverse domains, lengths and difficulty levels, without clear boundaries for threshold selection.As a result, the dependence of such input-sensitive threshold can be a fundamental limitation that causes large degradation on arbitrary inputs.In this work, we propose a new objective that lifts the threshold constraints for robust KV compression, advocating for “threshold-free” methods that adaptively adjust budget allocation while preserving full-cache performance.We then propose a novel method, ReFreeKV, serving as the first instantiation of this objective. Extensive experiments across 13 datasets with diverse context lengths, task types, and model sizes demonstrate its efficacy and efficiency. Our code is publicly released at https://github.com/Patrick-Ni/ReFreeKV.

ACL 2026

DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning

Pan Yang, Jing Yang, Ruan Xiao li, Yuling Chen, Yuankai Wu, Quan Zhou, Xu Wang

The core challenge of Compositional Zero-Shot Learning (CZSL) lies in learning representations of sub-concepts (attributes and objects) from seen compositions and recognizing unseen novel compositions. Most existing CZSL methods primarily focus on prompt optimization on the textual side, while overlooking insufficient visual attribute–object sub-concepts disentanglement under a text-centric paradigm. To this end, we propose DMSD, a Dual-Modal Semantic Disentanglement framework that jointly models visual and textual information to achieve effective sub-concept disentanglement. Specifically, DMSD introduces a Contextual Prompt Space, enabling both visual and textual modalities to be modeled under unified contextual semantic representations, thereby enhancing their alignment at the latent semantic level. Moreover, we design Visual Sub-concept Prototypes that explicitly extract and model visual sub-concept features, improving the independence and discriminability of visual sub-concept representations. Furthermore, to achieve fine-grained alignment between visual and textual sub-concepts, we propose a Class-Centroid Bridging Module that guides class centroids toward the textual semantic space, thereby ensuring cross-modal semantic consistency. Extensive experiments on three benchmark datasets (MIT-States, UT-Zappos, and C-GQA) demonstrate that DMSD achieves state-of-the-art performance in both closed-world and open-world settings. Our code is available at https://anonymous.4open.science/r/DMSD-9CC4.

ACL 2026

PseudoGD: Enhancing Spatial Reasoning in Vision-Language Models through Pseudo Geometric Knowledge Distillation

Gwanghee Lee, Yeeun Choi, Kyoungson Jhang

Recent Large Vision-Language Models (LVLMs) have shown remarkable success in general semantic understanding. However, they still struggle with 3D spatial reasoning tasks, such as estimating metric distances or understanding precise relative positions. Previous works, like SpatialVLM, tried to address this by using synthesized spatial VQA dataset. However, they are fundamentally limited because their vision encoders are biased toward 2D patterns learned from image-text pairs. In this paper, we argue that this lack of 3D awareness is a critical bottleneck that cannot be solved by data scaling alone. To address this, we propose Pseudo Geometric Distillation (PseudoGD), a framework designed to help vision encoders internalize 3D geometric information using only standard 2D images. PseudoGD explicitly injects metric scale and structural context into the encoder through a Joint Training strategy. This approach optimizes geometric learning and spatial VQA tasks together, ensuring that the Large Language Model (LLM) aligns well with the improved visual features in real-time. Extensive experiments on the OmniSpatial benchmark demonstrate that PseudoGD achieves State-of-the-Art (SOTA) performance across various model architectures. Notably, significant improvements in Hypothetical Perspective Taking and Locate tasks prove that our model has effectively learned a physical sense of space.

ACL 2026

View-R1: Asymmetric Policy Optimization for Difficulty-Aware Multimodal Reinforcement Learning

Minjie Hong, Zirun Guo, Jiabao Zhang, Zehan Wang, Ziang Zhang, Tao Jin, Zhou Zhao

Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data but often struggle with complex reasoning. Reinforcement learning (RL) can enhance reasoning, yet it may cause performance degradation on general tasks and overthinking in MLLMs. We propose Asymmetric Policy Optimization (APO), which separates responses into positive and negative groups. For positive samples, Difficulty-Adaptive Divergence Shaping (DADS) dynamically adjusts the KL weight to stabilize training and preserve knowledge. For negative samples, Suboptimal Trajectory Complexity Regularization (STCR) penalizes overly long responses to reduce overthinking. Applied to Qwen2.5-VL, our model View-R1 achieves a 10.55% improvement in reasoning and outperforms larger models (7–11B) while not only maintaining but also slightly improving performance on general tasks. These results highlight the effectiveness and broad applicability of our DADS and STCR techniques for advancing complex multimodal reasoning in MLLMs. Our code is available at https://github.com/Collab-Gen/View-R1.

ACL 2026

Multilingual Refusal Alignment for Safer Large Language Models

Aleksandra Krasnodębska, Wojciech Kusa, Aldo Lipani

As Large Language Models (LLMs) are deployed globally, ensuring their safety and alignment across multiple languages becomes paramount. However, safety behaviors often vary unpredictably between languages, posing significant challenges for consistent and ethical AI. In this work, we systematically investigate the dynamics of multilingual alignment, exploring whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities. We introduce RefusEU a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models. Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.

ACL 2026

LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment

Chenji Lu, Zhuo Chen, Hui Zhao, Zhiyuan Zeng, Gang Zhao, Junjie Ren, Lihaoran, Songyan Liu, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng

E-commerce search relevance is a critical component of retrieval systems. While Large Language Models (LLMs)-driven Chain-of-Thought (CoT) modeling has become the dominant paradigm and yielded significant gains, a critical gap remains: the absence of a systematic definition for comprehensive relevance reasoning, which leads to significant blind spots in current approaches. In this paper, we deconstruct the task into three core competencies: reasoning knowledge, multi-modal understanding, and rule awareness. Accordingly, we propose LoRE(Large Generative Model for Search Relevance), a novel two-stage training framework. We first employ an SFT phase to instill these capabilities via a progressive CoT synthesis pipeline, followed by a Reinforcement Learning(RL) phase, which serves as a regularizer, pruning redundant logic to achieve precise and robust adjudication. Extensive experiments validate LoRE, outperforming GPT-5 by 29.1% in Macro-F1 and achieving a 27% online gain, offering a vital reference for industrial domain-specific post-training.

ACL 2026

Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory

Sirui Liang, Pengfei Cao, Jian Zhao, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu

Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift. This paper proposes the Meta-Cognitive Memory Abstraction method (MCMA), which treats memory abstraction as a learnable cognitive skill rather than a fixed design choice. MCMA decouples task execution from memory management by combining a frozen task model with a learned memory copilot. The memory copilot is trained using direct preference optimization; it determines how experience should be structured, abstracted, and reused. Memories are further organized into a hierarchy of abstraction levels, enabling selective reuse based on task similarity. When no memory is transferable, MCMA transfers the ability to abstract and manage memory by transferring the memory copilot. Experiments on ALFWorld, ScienceWorld, and BabyAI demonstrate substantial improvements in performance, out-of-distribution generalization, and cross-task transfer over several baselines.

ACL 2026

Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization

Shan He, Runze Wang, Zhuoyun Du, Huiyu Bai, Zouying Cao, Yu Cheng, Bo Zheng

Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of “Agent Engineering.” Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural awareness to debug the intricate web of interactions in MAS. More critically, these optimizers are static; they do not learn from experience to improve their own optimization strategies. To address these gaps, we introduce Textual Parameter Graph Optimization (TPGO), a framework that enables a multi-agent system to learn to evolve. TPGO first models the MAS as a Textual Parameter Graph (TPG), where agents, tools, and workflows are modular, optimizable nodes. To guide evolution, we derive “textual gradients,” structured natural language feedback from execution traces, to pinpoint failures and suggest granular modifications. The core of our framework is Group Relative Agent Optimization (GRAO), a novel meta-learning strategy that learns from historical optimization experiences. By analyzing past successes and failures, GRAO becomes progressively better at proposing effective updates, allowing the system to learn how to optimize itself. Extensive experiments on complex benchmarks like GAIA and MCP-Universe show that TPGO significantly enhances the performance of state-of-the-art agent frameworks, achieving higher success rates through automated, self-improving optimization.

ACL 2026

AscendKernelGen: LLM-Driven Kernel Generation for NPUs

Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian

Neural Processing Units (NPUs) are critical for AI infrastructure, yet developing kernels remains a bottleneck due to the complexity of vendor-specific Domain-Specific Languages (DSLs). While LLMs excel in general coding, they fail to meet the stringent constraints of NPU development, showing a near-zero success rate on complex kernels in our preliminary study. To address these challenges, we present AscendKernelGen, the first comprehensive framework for NPU kernel development, marking a pioneering effort in this field. This framework consists of three interconnected components: (1) Ascend-CoT, the first dataset in the NPU kernel domain that incorporates chain-of-thought reasoning from real-world kernel implementations; (2) KernelGen-LM, a domain-adaptive model trained on this novel dataset using supervised fine-tuning and reinforcement learning; and (3) NPUKernelBench, the first benchmark platform designed to evaluate the compilation, correctness, and performance of generated NPU kernels. Experimental results demonstrate that our approach dramatically bridges the gap in hardware-specific coding: compilation success on complex Level-2 kernels improves from 0% to 95.5% (Pass@10), with 64% functional correctness. AscendKernGen is available at AscendKernGen and NPUKernelBench.

Keep browsing

More papers from top AI conferences

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