跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+672新增论文
+517其中 AI 相关
+80已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 11:16 — 2026-11-17 11:16(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

24,106 已收录论文20,158 AI 相关7,049 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 16 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
版本更新 · v3arXiv:2508.18370

Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

Terry Yue Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, Zijian Wang

原文摘要

Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through verified feedback loops. Yet, scalable and generalizable execution-grounded environments remain scarce, limiting progress in training more capable ML agents. We introduce CTF-Dojo, the first large-scale executable runtime tailored for training LLMs with verifiable feedback, featuring 658 fully functional Capture-The-Flag (CTF)-style challenges containerized in Docker with guaranteed reproducibility. To enable rapid scaling without manual intervention, we develop CTF-Forge, an automated pipeline that transforms publicly available artifacts into ready-to-use execution environments in minutes, eliminating weeks of expert configuration traditionally required. We trained LLM-based agents on just 486 high-quality, execution-verified trajectories from CTF-Dojo, achieving up to 9.9% absolute gains over strong baselines across three competitive benchmarks: InterCode-CTF, NYU CTF Bench, and Cybench. Our best-performing 32B model reaches 31.9% Pass@1, establishing a new open-weight state-of-the-art that rivals frontier models like DeepSeek-V3-0324 and Gemini-2.5-Flash. By framing CTF-style tasks as a benchmark for executable-agent learning, CTF-Dojo demonstrates that execution-grounded training signals are not only effective but pivotal in advancing high-performance ML agents without dependence on costly proprietary systems.

cs.SE · cs.CL · cs.CR · cs.LG

版本更新 · v3arXiv:2508.00910

Cyber-Zero: Training Cybersecurity Agents without Runtime

Terry Yue Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, Zijian Wang

原文摘要

Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are often unavailable in other domains, especially cybersecurity, where challenge configurations and execution contexts are ephemeral or restricted. We present Cyber-Zero, the first runtime-free framework for synthesizing high-quality agent trajectories to train cybersecurity LLMs. Cyber-Zero leverages publicly available CTF writeups and employs persona-driven LLM simulation to reverse-engineer runtime behaviors and generate realistic, long-horizon interaction sequences without actual environments. Using trajectories synthesized by Cyber-Zero, we train LLM-based agents that achieve up to 11.4% absolute performance gains over baseline models on three prominent CTF benchmarks: InterCode-CTF, NYU CTF Bench, and Cybench. Our best model, Cyber-Zero-32B, establishes new state-of-the-art performance among open-weight models, matching the capabilities of proprietary systems like DeepSeek-V3-0324 and Claude-3.5-Sonnet while offering superior cost-effectiveness, and demonstrating that runtime-free trajectory synthesis can effectively democratize the development of state-of-the-art cybersecurity agents.

cs.CR · cs.CL · cs.LG

新论文 · v1arXiv:2611.13843

PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard

Mohammed Nayeem Khan, Sarun Kumar K S

原文摘要

Typed-decision encoders answer a question about a text in one forward pass, but their behaviour outside English is rarely measured on a fixed yardstick. We release PolyRoute: 322 native-language support messages in 12 languages and 9 writing systems, 156 code-mixed or romanised messages (Hinglish, Spanglish, Arabizi), 967 optional native training rows, and a protocol for a three-way department-routing decision. Labels come from Qwen3.8-27B with a blind second pass (91% of candidates kept); an independent model, gemma4-31b, agrees on 97.2% of test items, and the largest character 5-gram similarity between any test text and any training text is 0.33. A leaderboard of 13 systems gives 61.2% for the English-root checkpoint, 77.3% for the shipped multilingual one and 96.6% for the best fine-tune; TF-IDF with logistic regression reaches 91.9%. On four withheld languages the three multilingual systems score 77%, 90% and 93%. On code-mixed text the English root (85%) is nominally ahead of the shipped multilingual checkpoint (79%; p=0.134). The split resolves differences only above about 4 points. All texts and labels are LLM-generated.

cs.CL · cs.AI

新论文 · v1arXiv:2611.10638

SLA-Aware Task Offloading in the IoT Edge-Cloud Continuum: Class-Weighted Deep Reinforcement Learning Against an Exact Optimum

Shilpa Golla, Tharun Kumar Korine Palli, Urmila Bandaru

原文摘要

Deep reinforcement learning (RL) is often used to decide where Internet of Things (IoT) tasks with different latency limits run in the edge-cloud continuum, yet some methods give every missed task the same penalty and few compare their agents with an optimal policy. This benchmark study builds four offloading systems small enough to solve exactly by dynamic programming and measures reward and learner against the optimum. A bonus for a met limit makes each miss cost its penalty plus the bonus, which shifts the class weights of published per-class rewards. A class-blind penalty stays 65% to 118% above the optimal cost even with a perfect learner, while a corrected per-class penalty comes within 0.13% of the optimum. With a per-class reward, tuned proximal policy optimization (PPO) agents come within 9% to 11% of the optimum in the smallest system, and the corrected one beats a tuned reservation rule in 9 of 10 seeds. In larger systems the agents stay 41% to 76% above the optimum, and a tuned rule beats their mean. Training ten times longer does not close this gap, and a PPO-Lagrangian agent with reachable targets does no better than the per-class reward.

cs.AI · cs.LG · cs.NI

新论文 · v1arXiv:2611.10635

Model-Based Imitation Learning For Monocular Vision-Based Navigation

Basant Sharma, Prajyot Jadhav, Saqi Hussain Kalan, Arun Kumar Singh

原文摘要

Reliable navigation with a single monocular limited field-of-view camera is challenging because the lack of depth measurements and limited spatial awareness complicate collision checking. Existing approaches to tackle these challenges fall into two categories. Model-based planners can incorporate explicit collision-avoidance guidance which leads to better generalization but are often computationally expensive and require manual tuning of the algorithmic parameters. In contrast, end-to-end approaches trained by imitation learning can be flexible but typically encode safety only implicitly and thus can suffer from high collision rates in novel scenarios. In this paper, we present a middle ground through model-based imitation learning. The model-based part is a learned collision model that can map a sequence of past images and a candidate control sequence to a distribution of worst-case obstacle clearance. This predictive distribution in turn is used to define a collision-risk cost in a trajectory optimization formulation. The imitation component uses human demonstrations to learn scene-dependent balancing of collision risk with other task costs such as goal progress. We also use it to learn the algorithmic parameters (e.g., a warm start) of our optimizer to accelerate the solution process. We show that our approach can demonstrate highly reliable navigation in cluttered environments on robots with different embodiments. We also demonstrate a substantial reduction in collision rate over recent end-to-end and model-based baselines.

cs.RO

版本更新 · v2arXiv:2605.20299

物理序列建模中误泛化的机制

Mechanisms of Misgeneralization in Physical Sequence Modeling

Kento Nishi, Raphael Tang, Karun Kumar, Core Francisco Park, Hidenori Tanaka

AI 速读 基于摘要

作者发现并形式化生成式序列模型在物理轨迹规划中出现的“物理误泛化”现象,即单条轨迹看似合理但物理量(如行程距离、机械能)的总体分布偏离数据设计意图,并提出基于数据偏差核的机制解释与缓解方法。

cs.LG · cs.AI · cs.RO

查看原文摘要

Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to train such a model, engineers may curate demonstrations to specify how trajectories should be distributed over a physical quantity like travel distance or mechanical energy. For example, a roboticist building a maze navigation agent might choose demonstrations whose travel distances cover a fixed range uniformly, hoping to constrain the agent's expected power usage. We find that standard deep learning can violate this intent: each generated trajectory can seem plausible on its own, but the aggregate distribution over the physical quantity is wrong. We call this failure physical misgeneralization. In this work, we identify and formalize the problem, develop and validate an account of its mechanism, and use that account to compare and design mitigations. Using controlled synthetic tasks, we show that physical misgeneralization arises when local errors typical of the model class propagate through the physical measurement to shift the recovered distribution. We estimate these errors with a data deviation kernel, and we use it to predict which physical quantity values gain or lose mass under real diffusion sequence models trained on both toy and applied trajectory generation tasks. Finally, our mechanistic interpretation helps identify which mitigations are structurally promising. We first compare interventions that modify the dataset and generative interface, then show that the mechanistic understanding we develop throughout this paper suggests a novel way to construct data representations informed by the kernel. We show that our proposed mitigation, which transforms the coordinate system under which the generator learns and samples, effectively reduces quantity drift.

新论文 · v1arXiv:2611.10099

Enmo Safety: External, Non-invasive, Model-agnostic Oversight for Off-the-Shelf Language Models

Mohammed Nayeem Khan, Sarun Kumar K. S., Allan Kevin T., Chirag Vaidya, Vrishank Tiwari

原文摘要

We study a safety harness that improves itself without touching model weights. Enmo Safety wraps a chat model with a deterministic input assessment, trigger-matched safety guidance, spotlighting of untrusted content, and an output guard. A reflector model turns failures into one bounded update per round, and an update is kept only if it lowers harm without raising refusal of benign prompts on a held-out dev split. Every version is snapshotted and every decision ledgered. We evaluate a bare model, the seed harness and the evolved harness on six open benchmarks (HarmBench, AdvBench, JailbreakBench, XSTest, AgentHarm, deepset prompt-injections). On 150 items and on a 290-item holdout, none of the before/after differences on two models was statistically significant. A fourth iteration ran six policy models on a fresh 300-item split: the harness cut the unsafe rate significantly on two models (12.9% to 7.1%, p = 0.035; 10.2% to 3.6%, p = 0.036), not on the other four, and raised agentic-harm labels on two. Whether the rules fired was unrelated to outcome (Fisher p from 0.30 to 1.0), and the helpfulness clauses made agentic harm worse than no harness on obfuscated attacks. A reworded clause and an input-normalisation step form harness v22, at a measured cost in benign tool-task refusal. Each cell is one run, so these estimates do not establish a general safety improvement. Code, harness versions and ledger: https://github.com/rioryugen/enmo_safety

cs.CR · cs.AI · cs.SE

新论文 · v1arXiv:2611.09270

EGT: Execution-Grounded Traversability through Learned Closed-Loop Trajectory Distributions

Chinmay Mundane, Amith Manoharan, Arun Kumar Singh

原文摘要

Rough terrain traversability is often estimated through point-wise roll, pitch, or force-angle margins along a planned path. However, these metrics are often inaccurate and overly conservative because they ignore how terrain disturbances and low-level controller corrections can affect the vehicle's motions. To overcome these limitations, we introduce Execution-Grounded Traversability (EGT), defined as the probability that a vehicle-controller pair can execute a candidate path while meeting trajectory-level tracking and progress requirements. We estimate EGT by predicting the distribution of closed-loop trajectories using a latent-space flow matching (FM) model conditioned on multi-resolution terrain features and 3D vehicle attitude and wheel-ground contact points prior. Across 650 simulated trials on unseen terrains, EGT reduces safe-path rejection to 2.2% (versus 11.4%-39.5% for pose-margin and force-angle baselines) and unsafe acceptance to 7.7%. Integrated into a receding-horizon sampling-based planner, EGT reduces navigation failure rates by 24-42 and 30-44 percentage points over [1] and [2], respectively, while cutting goal-reaching time by up to 20.5% and 45%. Finally, we demonstrate zero-shot transfer of our simulation-trained model to real-world outdoor experiments.

cs.RO

版本更新 · v2arXiv:2608.02946

Sedentary Behavior Classification for Wearable Sensors with a CNN-BiLSTM Model

Yuliang Chen, Weiwei Shi, Rong Zablocki, Animesh Kumar, Jordan A. Carlson, Sheri J. Hartman, Mikael Anne Greenwood-Hickman, Paul R. Hibbing 等 13 位作者

原文摘要

Accurate detection of sedentary behavior is important for studying health risks related to prolonged sitting, but posture-based classification remains challenging with wearable sensors, especially at the wrist. We study whether a deep learning model trained on hip-worn accelerometer data can transfer to wrist-worn accelerometer data for sitting versus non-sitting classification. We use CHAP, a CNN-BiLSTM model originally developed for hip accelerometers, and evaluate its zero-shot performance on wrist data as well as its adaptation through finetuning with varying amounts of labeled wrist data. Experiments are conducted on the iWatch dataset with ground-truth posture labels derived from wearable cameras. The hip-trained model performs strongly on hip data without retraining, but accuracy drops on wrist data due to sensor placement shift. Finetuning CHAP provides consistent advantages over transformer models trained from scratch. These findings suggest that hip-based pretraining provides a useful starting point for wrist deployment, while highlighting the need for wrist-specific adaptation to handle higher signal variability.

cs.LG

新论文 · v1arXiv:2610.40050

Don't Risk It!: Trajectory-Conditioned Distributional Risk for LiDAR-Only Crowd Navigation

Mathai Mathew Pulicken, Laksh Nanwani, Basant Sharma, Phani Teja Singamaneni, Arun Kumar Singh, K. Madhava Krishna

原文摘要

Efficient crowd navigation requires anticipating dynamic collision-free space without relying on fragile object tracking. We propose the Don't Risk It Planner (DRIP), an end-to-end LiDAR-only planning framework that couples occupancy forecasting with trajectory-conditioned clearance and uncertainty estimation. Operating directly on LiDAR-derived occupancy grid histories, DRIP predicts a distribution over minimum robot-obstacle clearance for candidate control sequences to evaluate collision risk. The model is trained using a risk cost that grounds predictive uncertainty directly in empirical collision outcomes rather than geometric regression alone. In closed-loop experiments with up to 45 pedestrians, DRIP achieves higher success rates with fewer collisions and reduced freezing behavior compared to state-of-the-art baselines.

cs.RO

新论文 · v1arXiv:2610.39468

Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering

Mohammed Nayeem Khan, K S Sarun Kumar

原文摘要

AI coding agents now do long, multi-step and multi-session software work with little supervision. When a developer comes back to that work, the useful question is not what the model said but what was actually done, by whom, and whether it is finished. We study this in three parts. First, we verify Agenttrail, an open-source local observability tool for coding agents, against its source at commit e4ba2da: nine documented constants and mechanisms hold at file-and-line level, two event pipelines are never unified, and its Map service has an unauthenticated local mutation surface. Second, we run a prototype of our system on 45 real coding-agent sessions (102,233 records, 20,577 tool executions, 2,336 human-to-agent episodes). With a blind-audited classifier (precision 83.3% and 96.7%) we estimate that 23.4% (95% CI 17.1 to 35.7) of code-editing episodes end with no independent check after the last edit, and that 57.8% of to-dos the agent marked complete after editing had no proof in between. A 10-minute timing heuristic for session hand-offs recovers 6 of the 24 session pairs that content lineage links. 42% of sessions run longer than 24 hours, 48.1% of transcript bytes lie past a 2 MiB replay bound, and 1,326 records in 16 sessions contain credential-like strings. Third, we propose Soei (Structured Observability of Evidence and Intent): an acknowledgement-aware event schema, a hash-chained local ledger, a W3C PROV-aligned graph, calibrated inference for attribution and lineage, and a verification layer that keeps a claim of completion apart from proof. On the same corpus the ledger is 20% of raw size, holds no content or credentials, verifies at about 126k events/s, detects tampering and replays deterministically. We position the work against concurrent 2026 proposals and define autonomy levels with evidence gates and harness metrics baselined on our data.

cs.SE · cs.AI · cs.MA

新论文 · v1arXiv:2610.37585HF 社区推荐

Timestral

Adrien Petralia, Alexandre Gavaudan, Artjom Joosen, Etienne Goffinet, Richard Kurle, Yassine El Ouahidi, Yassir Bendou, Abdelaziz Bounhar 等 356 位作者

原文摘要

We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and Timestral-123M take the top two places on every metric. We achieve this with three ingredients: Decoupled Horizon Forecasting (DHF), which separates prediction tokens from the causally encoded context, so that longer horizons are trained without masking context and each observed value is both a forecast target and context for later forecasts; a covariate framework that natively supports known-future covariates within a causal architecture; and a two-stage pipeline that pretrains exclusively on a diverse, large-scale synthetic corpus before post-training on a mix of real and synthetic data with extended context. This report describes the model design and its benchmark results. Weights for all four models are available on Hugging Face and inference code on GitHub.

cs.AI

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1962ACL Anthology · ACL 2026

Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization

Yifeng Ding Meta FAIR and Department of Computer Science, University of Illinois at Urbana-Champaign, Hung Le, Songyang Han NVIDIA, Kangrui Ruan AWS AI Lab, Zhenghui Jin NVIDIA, Varun Kumar Amazon, Zijian Wang Meta Superintelligence Labs, Anoop Deoras

原文摘要

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) – where models iteratively reason, generate code, and verify through execution – remains challenging for existing reinforcement learning (RL) approaches. Current RL methods, exemplified by Group Relative Policy Optimization (GRPO), suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation. To address this issue, we propose Group Turn Policy Optimization (GTPO), a novel RL algorithm specifically designed for training LLMs on multi-turn TIR tasks. GTPO introduces three key innovations: (1) turn-level reward assignment that provides fine-grained feedback for individual turns, (2) return-based advantage estimation where normalized discounted returns are calculated as advantages, and (3) self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards. Our comprehensive evaluation demonstrates that GTPO outperforms GRPO by 3.0% across diverse math reasoning benchmarks, establishing its effectiveness. GTPO also improves GRPO by 3.9% on commonsense reasoning and program synthesis tasks, demonstrating its generalizability to non-math domains. Importantly, GTPO incurs negligible overhead, ensuring its practicality for real-world scenarios.

cs.CL · cs.AI

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.2142ACL Anthology · ACL 2026

CEBC: Conformal Evidence-Bounded Control for Low-Hallucination Vision–Language Generation

Ashish Mishra hewlett packard enterprise, Tarun Kumar, Arpit Shah Gujarat Technological University Ahmedabad, Suparna Bhattacharya Hewlett Packard Enterprise, Martin Foltin Hewlett Packard Enterprise

原文摘要

Hallucinated object mentions remain a persistent failure mode of vision–language models (VLMs) across generation tasks such as image captioning and visual question answering: outputs may be fluent yet include entities not supported by visual evidence. Existing mitigation approaches often reduce hallucinations at the cost of degraded generation quality or require expensive retraining and task-specific supervision. We introduce CEBC, a lightweight, training-free framework for low-hallucination vision–language generation based on conformal evidence-bounded minimal editing. CEBC first produces a strong base output (via greedy decoding or best-of-K sampling), then applies an evidence-bounded editing step that minimally revises or suppresses unsupported object mentions using constraints derived from an external visual detector. Crucially, the evidence threshold is conformally calibrated on a small held-out set via quantiles of detector confidence scores, enabling explicit and controllable hallucination risk at test time.To balance factuality and informativeness, we further introduce a risk-first, quality-aware selection rule that prioritizes evidence-consistent generations while regularizing unnecessary length or lexical drift. Extensive experiments on MS-COCO and GQA for image captioning, and POPE for VQA evaluation across multiple VLMs demonstrate that CEBC consistently reduces hallucination rates(CHAIR_S, CHAIR_I, POPE) while maintaining or improving standard generation quality metrics (CIDEr, BLEU, CLIPScore). CEBC establishes a stronger factuality–quality Pareto frontier without any additional model training or access to paired supervision beyond an off-the-shelf detector.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.607ACL Anthology · ACL 2026

CODESTRUCT: Code Agents over Structured Action Spaces

Myeongsoo Kim Amazon, Chao-Chun Hsu Amazon, Dingmin Wang Amazon, Shweta Garg, Varun Kumar Amazon, Murali Krishna Ramanathan Amazon

原文摘要

LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action space where agents operate on named AST entities rather than text spans. Our framework, CodeStruct, provides readCode for retrieving complete syntactic units and editCode for applying syntax-validated transformations to semantic program elements. Evaluated on SWE-Bench Verified across six LLMs, CodeStruct improves Pass@1 accuracy by 1.2-5.0% while reducing token consumption by 12-38% for most models. Models that frequently fail to produce valid patches under text-based interfaces benefit most: GPT-5-nano improves by 20.8% as empty-patch failures drop from 46.6% to 7.2%. On CodeAssistBench, we observe consistent accuracy gains (+0.8-4.4%) with cost reductions up to 33%. Our results show that structure-aware interfaces offer a more reliable foundation for code agents.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.786ACL Anthology · ACL 2026

SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion

George Ma University of California, Berkeley, Anurag Koul Amazon, Qi Chen Amazon, Yawen Wu Amazon, Sachit Kuhar Amazon, Yu Yu Hark and Amazon, Aritra Sengupta Amazon, Varun Kumar Amazon 等 9 位作者

原文摘要

Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting repository context at inference time. Low inference time latency budget either affects retrieval quality or the added latency impacts user experience adversely. We address this limitation with SpecAgent, an agent that enhances both latency and code-generation quality by proactively exploring repository files during indexing and constructing speculative context that anticipates future edits in each file. This indexing-time asynchrony allows thorough context computation masking latency and the speculative nature of the context improves code-generation quality. Additionally, we identify the problem of future context leakage in existing benchmarks, which can inflate reported performance. To address this, we construct a synthetic, leakage-free benchmark that enables a more realistic evaluation of our agent against baselines. Experiments show that SpecAgent consistently achieves absolute gains of 9–11% (48–58% relative) compared to the best-performing baselines, while significantly reducing inference latency.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表