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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 19:13 — 2026-11-16 19:13(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44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。

23,827 已收录论文19,941 AI 相关6,921 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 39 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2611.12762

Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery

Weida Wang, Benteng Chen, Yigeng Jiang, Shuchen Pu, Weiping Shen, Zichao Liu, Yulin Su, Zitong Wang 等 90 位作者

原文摘要

We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these assessments to adapt research targets and select reusable reasoning methods. On Taiyi-Bench, an AI co-scientist ideation benchmark comprising 265 tasks from 50 papers across ten disciplines, Sage-Taiyi ranks first on all eight metrics of historical rediscovery and open-ended ideation, achieving an Overall score of 54.0 compared with 47.9 for the strongest baseline, AI Scientist-v2. It also performs well on two external scientific ideation benchmarks. Five expert-guided collaborations further connect its proposals to experimental and computational validation across chemistry, materials science, and engineering. In chemistry, reaction-condition optimization raises the yield of cobalt-catalyzed carbonylation from trace amounts to 84% and photocatalytic allylic amination from 13% to 69%. These results support metacognitive regulation as an approach to scientific ideation and its progression toward practical validation.

cs.AI

版本更新 · v3arXiv:2508.02001

Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC

Chungang Lin, Xuying Meng, Tianyu Zuo, Weiyao Zhang, Meng Shen, Ruijie Zhao, Guanming Che, Ruiqi Meng 等 12 位作者

原文摘要

Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert service degradation and vulnerabilities. These pressures have produced two research lines that advance 1) versatile analysis, via network foundation models for low label dependency, and 2) efficient analysis, via hardware offloading for low analysis latency. However, co-achieving versatility and efficiency via such lines has appeared incompatible, with prior work advancing one while compromising the other, yet we show that this incompatibility is a consequence of polarized design choices across the three components of traffic analysis systems, i.e., traffic processing, model architecture, and analysis execution. In response, we present Nepco, a versatile yet efficient network traffic analysis system that offloads network foundation models to SmartNIC. Our key observation is that discriminative traffic information often exhibits localized patterns within byte sequences, motivating versatile yet efficient localized byte-sequence modeling. To exploit this without incurring the latency bottlenecks of complex encoding steps, we employ a hardware-friendly processing strategy that directly embeds raw byte sequences. To maintain versatility across diverse tasks characterized by spatially shifting features, we explore an observation-driven convolution architecture equipped with hardware-friendly scoring and gating designs. By exploiting translation invariance, this design dynamically locates and extracts salient semantic signatures irrespective of their byte-level offsets. We prototype Nepco on the NVIDIA BlueField-3 SmartNIC with multi-engine collaborative analysis execution. The experimental results demonstrate that Nepco achieves macro F1 competitive with the best performances achieved by 8 state-of-the-art network foundation models...

cs.NI · cs.LG

版本更新 · v3arXiv:2406.04428

MoralBench: Moral Evaluation of LLMs

Jianchao Ji, Yutong Chen, Mingyu Jin, Wujiang Xu, Wenyue Hua, Yongfeng Zhang

原文摘要

In the rapidly evolving field of artificial intelligence, large language models (LLMs) have emerged as powerful tools for a myriad of applications, from natural language processing to decision-making support systems. However, as these models become increasingly integrated into societal frameworks, the imperative to ensure they operate within ethical and moral boundaries has never been more critical. This paper introduces a novel benchmark designed to measure and compare the moral reasoning capabilities of LLMs. We present the first comprehensive dataset specifically curated to probe the moral dimensions of LLM outputs, addressing a wide range of ethical dilemmas and scenarios reflective of real-world complexities. The main contribution of this work lies in the development of benchmark datasets and metrics for assessing the moral identity of LLMs, which accounts for nuance, contextual sensitivity, and alignment with human ethical standards. Our methodology involves a multi-faceted approach, combining quantitative analysis with qualitative insights from ethics scholars to ensure a thorough evaluation of model performance. By applying our benchmark across several leading LLMs, we uncover significant variations in moral reasoning capabilities of different models. These findings highlight the importance of considering moral reasoning in the development and evaluation of LLMs, as well as the need for ongoing research to address the biases and limitations uncovered in our study. We publicly release the benchmark at https://drive.google.com/drive/u/0/folders/1k93YZJserYc2CkqP8d4B3M3sgd3kA8W7 and also open-source the code of the project at https://github.com/agiresearch/MoralBench.

cs.CL · cs.AI

新论文 · v1arXiv:2611.15135

ARTS: An Open-Source, Reproducible Three-Arm Platform for Autonomy Research in Minimally Invasive Surgery

Jiawei Ge, Chunwoo Kim, Antony Goldenberg, Douglas McDonough, Justin Liao, Bo Ning, Sylvia Ladstaetter, Katya Van Anderlecht 等 21 位作者

原文摘要

Research on surgical autonomy needs open platforms that any laboratory can build, yet the most widely shared platform depends on donated clinical hardware, and open alternatives on industrial arms each lack part of the surgical chain. We present the Autonomous Robotic Translational System (ARTS), an open-source three-arm platform for autonomy research in minimally invasive surgery, built entirely from purchasable parts for about USD 137,000. Two UR5e arms hold wristed da Vinci X/Xi instruments, a UR5 arm holds a stereo endoscope with two FLIR cameras, the surgeon console provides haptic handles, footswitches and a stereo viewer, and a hardware stop independent of the software lets a supervisor freeze all three arms in place. The ROS 2 software pins every dependency, installs from the same scripts on bare metal or in containers, and records stereo images with hardware-measured timing. On the real arms, ARTS commands each arm at its controller's full rate (e.g., 500 Hz on the UR5e), the two cameras expose within 12 microseconds of each other, hand motion reaches the arm in 58 ms, and the endoscope image reaches the monitor in 68 ms. The ISO 9283 pose repeatability is 0.14-0.25 mm, comparable to a da Vinci Research Kit (dVRK) Classic arm on the same protocol, and an optical tracker measured a mean remote-center-of-motion error of 0.34-0.37 mm. Three expert and three novice operators performed the Fundamentals of Laparoscopic Surgery (FLS) peg transfer through a laparoscopic trainer box, and one of the experts sutured on a suture pad. The hardware designs, firmware and software are available at https://github.com/MRE-Lab-UMD/arts.

cs.RO

版本更新 · v3arXiv:2605.10664

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions

Diancheng Kang, Zheyuan Liu, Ningshan Ma, Yue Huang, Zhaoxuan Tan, Meng Jiang

原文摘要

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key failure mode: steered token states are stored and repeatedly reused, turning a local perturbation into cumulative coherence degradation. To address this challenge, we propose Gated Cropped Attention-Delta steering (GCAD), which extracts steering signals from system-prompt contributions to self-attention and applies them with token-level gating. Across persona-steering experiments, GCAD preserves trait control while substantially improving long-horizon coherence. On the main multi-turn benchmark, GCAD improves average coherence drift from -18.6 to -1.9 and raises turn-10 trait expression from 78.0 to 93.1. These results suggest that activation steering becomes more reliable when interventions follow the prompt-mediated pathways that models already use for behavioral control.

cs.CL · cs.AI

新论文 · v1arXiv:2611.11689

Declarative DNS - Resolving Recursive Resolution

Felix Linker, Yue Huang, David Basin, Huayi Duan

原文摘要

DNS zone configuration errors are a frequent source of outages and frustration, particularly in combination with DNSSEC. Research has attempted to address the problem of zone configuration errors using formal methods, but existing proposals (i) only verify the absence of specific, known configuration errors, and (ii) do not consider DNSSEC. We present a new formal model of the DNS that covers most of DNSSEC, making it one of the most complete DNS models to date. In addition, we present a new tool, DecDNS, that performs a resolvability change-impact analysis of zone configuration updates using our model. We show that such a change-impact analysis can identify configuration errors without explicitly searching for them. We evaluate DecDNS both formally and empirically. We prove that DecDNS is sound and complete and show that its results agree with widely used DNS software. Finally, we explain how our approach can be integrated into operational practice, helping guide zone management in the real world.

cs.LO · cs.NI

新论文 · v1arXiv:2611.11650

FlowEval: How Much Adaptation Does an Embodied Foundation Model Need at Deployment?

Zhang Xi-Jia, Roman Yakunin, Shivang Chopra, Chengyue Huang, Che Chen, Siddharth Karamcheti, Zsolt Kira

原文摘要

Large-scale pretraining is reducing the amount of adaptation required to deploy embodied foundation models, but it is not guaranteed that a pretrained model already provide the level of performance required in every deployment. Practitioners therefore need to understand how well a pretrained model matches a target deployment and how much adaptation data is left to be collected. We study whether a small set of successful target-domain demonstrations can reveal whether and how much target-domain data will be required before any adaptation. We introduce FlowEval, a set of training-free metrics that use the flow-matching objective to probe an embodied foundation model with a set of demonstrations. FlowEval quantifies predictive disagreement on successful target demonstrations to assess how well a pretrained model fits a target deployment. Across four embodied foundation model families: Pi-0.5, MolmoAct2, GR00T, and DreamZero, FlowEval distinguishes seen from unseen deployments across real-world and simulated manipulation. Further, by finetuning Pi-0.5 and GR00T on 17 RoboCasa365 manipulation tasks, we showed that FlowEval correlates with how success rate improves as additional adaptation data is provided. Together, these results suggest that FlowEval can serve as a lightweight, training-free diagnostic of how much model--deployment adaptation may be required.

cs.RO

版本更新 · v2arXiv:2606.30015

参数化技能

Parametric Skills

Xuan Zhao, Haonan He, Qingyu Yang, Minglei Li, Zelin Tan, Bo Wan, Jingqi Ye, Chen Zhang 等 10 位作者

AI 速读 基于摘要

提出 ParametricSkills 框架,在测试时将文本技能转化为 LoRA 适配器,实现无需占用上下文的技能全生命周期管理。

cs.CL

查看原文摘要

For LLMs, skills are textual recipes encoding mature problem-solving experience. Despite widespread deployment, their utility is limited by the model's ability to comprehend and follow skill instructions. To address this limitation, we propose ParametricSkills, a framework that parameterizes textual skills at test time, enabling context-free management of the full skill lifecycle. Specifically, we first construct a large-scale and high-quality skill collection, and then synthesize single-turn and multi-turn skill-exploitation trajectories. Using this data, we then train a hypernetwork that parameterizes both the content and the exploitation methodologies of skills by converting textual skills into LoRA adapters. To facilitate the real-world application of our framework, we further align the hypernetwork on complex, long-horizon trajectories collected with OpenCode, enabling the models to operate reliably in realistic interactive workflows with ParametricSkills. Across evaluations, ParametricSkills effectively parameterizes skills, yielding substantial gains in task completion. More notably, as parametric skills accumulate as adapters rather than crowding the context, they open a preliminary but promising path toward continual learning at test time.

新论文 · v1arXiv:2611.07235

Adaptive Hybrid Force-Vision Control with EMG-Derived References for Deformable Bottle Manipulation

Jeffrey Lee, Geoffrey Hanks, Evangeline Bouganim, Yue Hu

原文摘要

Robotic automation of laboratory tasks has become a growing interest to remove researchers from hazardous environments and repetitive procedures. However, even equipment as simple as squeeze bottles poses a challenging manipulation problem due to its deformability. This paper presents an adaptive hybrid vision-force controller for robotic grippers to effectively manipulate laboratory squeeze bottles to dispense liquid. This approach integrates force and vision feedback according to the interaction state, enabling effective squeezing while accounting for bottle deformation and recovery. The proposed controller is validated by comparing its performance with a pure force controller on 12 combinations of conditions consisting of 2 target dispense volumes, 2 plastic squeeze bottles, and 1 to 3 squeezes used to dispense. Human demonstrations of these operating conditions were collected using electromyography (EMG) sensing mapped to a desired grip force, which was then used as the force reference for the controllers to squeeze the bottles. Results demonstrated that the proposed adaptive hybrid vision-force controller achieved more accurate liquid dispensing with a mean absolute error (MAE) of 6.54 mL compared to a MAE of 15.92 mL from the pure force controller, while also replicating the human action recorded from the EMG signal more closely.

cs.RO

新论文 · v1arXiv:2611.05551

VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas

Pengze Li, Jingna Feng, Yue Yu, Yining Wu, Xinyue Hu, Jie Lin, Avanti Bhandarkar, Cui Tao

原文摘要

Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represented in the available data and applied consistently across the workflow. These decisions depend on local data representations and operational conventions and can involve source selection, patient and encounter identity, linkage, and temporal interpretation. Here we introduce VirtualTrialHarness (VTHarness), an agent framework that coordinates virtual-trial operationalization by selecting reusable procedural skills for each workflow stage and uses explicit contracts to maintain consistent study decisions across stages. We also introduce VTBenchmark for evaluating source selection and cohort construction. Across three complex synthetic environments, VTHarness successfully produced all required cohort outputs matching the references in 95.1% of workflows after requirement clarification, compared with 60.4% using retrieval from the same procedural corpus. Procedural skills improved source recovery across three language models and increased source overlap with analyst code in 13 Mayo Clinic cases. Site-specific adaptation enabled reference-matched cohort execution across eight MIMIC-IV tasks. Within the Mayo Clinic Virtual Trials Program, the framework supported investigator review of cohort construction and endpoint analysis. These findings support coordinating procedural guidance with workflow decisions to improve virtual-trial implementation across complex clinical schemas.

cs.AI

版本更新 · v3arXiv:2610.34527

LLM4Robot-Bench: How Far Can GPT-6 Astra Go in Robotic Manipulation? A Hierarchical, Paired Sim-Real Benchmark

Haibao Yu, Jiaqi Meng, Zijian Zhang, Bowen Jing, Lei Yang, Yue Hu, Chenchen Ge, Yiming Hou 等 19 位作者

原文摘要

We introduce LLM4Robot-Bench, a hierarchical, paired Sim-Real benchmark for evaluating physical interaction capabilities in contact-rich manipulation. Its 16 household tasks span three cumulative levels: contact selection and geometric alignment (L1), force regulation within sustained contact (L2), and coordinated contact reconfiguration and force regulation (L3). Each task is instantiated in physically and visually matched simulated and real-world environments, with shared task definitions and success criteria. We evaluate GPT-6 Astra zero-shot with three trials per task in each environment. Real-world success rates decline from 80.0% at L1 to 47.6% at L2 and 0.0% at L3, with corresponding simulation rates of 66.7%, 47.6%, and 0.0%. Ten of the 16 tasks have identical success counts across environments; the remaining six differ by one success out of three trials. Across both environments, recurring difficulties in spatial reasoning, contact selection, force regulation, and coordination often prevent local physical progress from accumulating into task completion. These findings characterize Astra's observed capability boundary across increasing interaction demands and, for this model, support matched simulation as a repeatable, scalable testbed for studying the sustained, coordinated physical interactions that limit reliable manipulation.

cs.RO

版本更新 · v2arXiv:2611.00769

DramaVQA: Probing Detailed Understanding of Ultra-Long TV Dramas

Xinyue Huo, Pengfei Chen, Jiannan Ge, Kaiwen Duan, Jiacheng Shao, Yunning Cao, Lingxi Xie, Qi Tian

原文摘要

Despite recent progress in long-form video understanding, current benchmarks mostly focus on short clips or hour-scale videos. This leaves a major gap in evaluating ultra-long video understanding, where videos often last tens of hours. To bridge this gap, we introduce DramaVQA, a large-scale benchmark built upon long-form TV dramas. Containing approximately 20K question-answering (QA) pairs, the scale of DramaVQA exceeds previous long-video datasets, such as Video-MME and LVBench, by an order of magnitude. Our benchmark has two main features that make it stand out from existing datasets. First, we establish a scalable, LLM-assisted annotation pipeline that uses multimodal large language models (MLLMs) to generate complex questions, followed by strict human checking to ensure high data quality. Second, DramaVQA introduces a multi-level time structure; queries are designed across different video lengths, with the hardest questions requiring overall understanding across the entire drama. Extensive evaluations show that state-of-the-art MLLMs face major challenges when tested on these very long videos, highlighting the need for agentic AI algorithms capable of managing long-term memory. The project is available at https://github.com/xinyuehuo/DramaVQA

cs.CV

版本更新 · v2arXiv:2607.07181

Three classes of few-weight self-orthogonal projective codes and their applications for LCD codes

Yue Huang, Zhonghao Liang, Chenlu Jia, Yongkang Wan, Qunying Liao

原文摘要

Since self-orthogonal codes, few-weight codes and linear complementary dual codes(LCD codes, for short) have nice applications in coding theory and cryptography, they have received continuous attention. In 2024, by introducing the notion of the augment code, Heng et al.[16] constructed several classes of few-weight self-orthogonal codes basing on defining sets, which are introduced by Ding et al.[7] in 2007. In this manuscript, for two classes of defining sets, we consider the corresponding augmented codes, construct three classes of four-weight self-orthogonal projective codes and determine the parameters of their dual codes. And then, we construct three classes of LCD codes. In particular, we prove that there exists a class of these LCD codes whose dual codes are almost optimal LCD codes according to the sphere packing bound.

cs.IT

新论文 · v1arXiv:2611.02667

UPSHIFT: User Preference Steering from Human-AI Interaction Feedback Traces

Jingping Wang, Zhanhao Li, Shao Zhang, Shuyue Hu

原文摘要

Personalizing large language model assistants requires adapting their responses to individual users, including the selection of content, reasoning approach, level of detail, and form of presentation. Such preferences are often latent, becoming visible only when users respond to an initial answer and request revisions. We investigate whether these feedback trajectories can be converted into a reusable personalization signal without explicit preference profiles or labels, prompt-time access to interaction histories, or model parameter updates. We introduce UPSHIFT (User Preference Steering from Human-AI Interaction Feedback Traces), a training-free method that compares the hidden representations of initial and feedback-conditioned responses within each session, averages the resulting trajectory displacements across a user's sessions, and injects the aggregated preference direction when answering a new query. The method is motivated by the implicit-preference hypothesis: although an individual conversational transition may reflect topic progression or task-specific correction, changes that recur across sessions retain a component that captures how the user wants responses to be adjusted. We validate the preference-representation capability of UPSHIFT on PrefEval. In evaluations with 40 simulated users, every tested configuration improves preference alignment over the unsteered baseline on held-out topics for both Qwen3-8B and Qwen3-32B; the best configuration increases macro-averaged Elo from 1364.0 to 1605.2 and from 1341.9 to 1591.8, respectively. Matched-user and positive-versus-negative controls further demonstrate that these gains arise from the user-specific preference direction and its learned orientation. These results show that interaction histories can provide compact, reusable supervision for lightweight personalization.

cs.AI

版本更新 · v2arXiv:2604.02686

Fooling Reward Models with Gibberish: Adversarial Examples Beyond the Semantic Regime

Yuheng Zhang, Mingyue Huo, Minghao Zhu, Mengxue Zhang, Nan Jiang

原文摘要

Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF). We show that leading RMs can assign higher scores to gibberish than to meaningful reference answers. To systematically discover such inputs, we introduce Token Mapping Perturbation Attack (TOMPA), a framework that uses a perturbed token mapping to extend an attack LLM's search beyond natural language. The mapping changes the linguistic meaning of the attack LLM's natural language responses, producing non-linguistic text for the target RM to score. We then use these scalar scores as rewards to train the attack LLM through reinforcement learning to discover non-linguistic adversarial inputs. Experiments against Llama and Qwen RMs demonstrate such attacks using two instantiations: identity token mapping across different tokenizers and random permutation with a shared tokenizer. Against Skywork-Reward-V2-Llama-3.1-8B, ranked first on RewardBench 2, the two mappings achieve mean rewards of +33.64 and +43.78, respectively, compared with +17.48 for GPT-5 reference answers. Their attack success rates are 97.6% and 100%, measured as the percentages of individual responses scoring above their corresponding GPT-5 references. These results show that strong benchmark performance does not ensure robustness to non-linguistic adversarial inputs, exposing a fundamental vulnerability in using RMs as optimization targets.

cs.LG · cs.AI

新论文 · v1arXiv:2611.01927

Is Your Long-Horizon Benchmark Really Deep? Measuring and Synthesizing Depth in Terminal Tasks

Yu Jiang, Yue Huang, Hang Hua, Yuyang Wu, Zixuan Weng, Olexandr Isayev, Yue Zhao, Zinan Lin 等 9 位作者

原文摘要

Long-horizon terminal tasks are used to evaluate and train agents. Human-curated datasets are scarce, so many synthesis methods have emerged. They usually measure the length of a task by the turns a model needs to pass it, and its difficulty by labels the LLM sets during generation. We find, however, that the turn count largely reflects the habits of the model, not only the demands of the task, and that the labels barely track how often models pass. We describe a terminal task by its work, the number of operations it requires, and its depth, the number of turns that must happen in sequence because the commands of each turn can only be chosen after reading the output of the previous one. Estimating depth as the smallest turn cap, stated to the agent, under which the task passes, we audit 734 tasks from six existing datasets. Synthesis has mostly added work, not depth: 94% of the solved synthetic tasks pass within three turns, yet depth, unlike the turn count, predicts difficulty beyond work. We propose DEPTH, in which a generation agent writes each task one segment at a time in a real software environment, carrying out each segment before writing it and starting the next from the state it leaves. Our 105 tasks exceed every audited dataset in depth and work, and none of six current models passes half of them. Fine-tuning Qwen3-8B on runs from these tasks improves it on two terminal benchmarks.

cs.AI

版本更新 · v4arXiv:2603.27771

生成式多智能体系统中的涌现风险

Emergent Risks in Generative Multi-Agent Systems

Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen 等 15 位作者

AI 速读 基于摘要

该研究考察由大生成模型构成的多智能体系统在共享资源竞争、顺序交接与集体决策等场景中自发出现的群体性失败模式。

cs.MA · cs.CL · cs.CY

查看原文摘要

Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems promise unprecedented scalability and autonomy, their collective interaction also gives rise to failure modes that cannot be reduced to individual agents. Understanding these emergent risks is therefore critical. Here, we present a pioneer study of such emergent multi-agent risk in workflows that involve competition over shared resources (e.g., computing resources or market share), sequential handoff collaboration (where downstream agents see only predecessor outputs), collective decision aggregation, and others. Across these settings, we observe that such group behaviors arise frequently across repeated trials and a wide range of interaction conditions, rather than as rare or pathological cases. In particular, phenomena such as collusion-like coordination and conformity emerge with non-trivial frequency under realistic resource constraints, communication protocols, and role assignments, mirroring well-known pathologies in human societies despite no explicit instruction. Moreover, these risks cannot be prevented by existing agent-level safeguards alone. These findings expose the dark side of intelligent multi-agent systems: a social intelligence risk where agent collectives, despite no instruction to do so, spontaneously reproduce familiar failure patterns from human societies.

版本更新 · v2arXiv:2610.26676

Which Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic Workflows

Qian Xie, Wenyue Hua, Yueli He, Sripad Karne, Armaan Agrawal, Nikos Pagonas, Eugene Wu, Kostis Kaffes 等 10 位作者

原文摘要

LLM agentic workflows increasingly employ different models for specialized roles. Users may prefer different trade-offs between task quality and deployment cost, sometimes also considering latency. Finding good assignments incurs a separate search cost from evaluating multiple candidates. We introduce Cost-Coupled Gittins (CC-Gittins), a multi-objective extension of single-objective cost-aware Gittins search for Pareto recommendation. It exploits the coupling between evaluation and deployment costs: assignments that cost more to deploy also cost more to evaluate. The search alternates between seeking higher quality and lower deployment cost, reusing each evaluation to inform both searches. After each batch, CC-Gittins recommends assignments that are nondominated under uncertainty-adjusted estimates of quality and deployment cost. We evaluate CC-Gittins on eight quality--cost matrices from workflows with two to five roles and up to 1,681 candidate assignments. We also evaluate the method with latency as a third objective. Across the eight benchmarks, CC-Gittins recovers a substantial fraction of the true Pareto frontier at roughly 10% of the exhaustive-evaluation cost, and recovers most of the frontier with few false positives by 30%.

cs.LG · cs.CL · stat.ML

新论文 · v1arXiv:2610.38095

Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI

NVIDIA, :, Aastha Jhunjhunwala, Aayushi Ashokkumar Srivastava, Abhibha Gupta, Abhinav Garg, Abhinav Khattar, Achsah Wildish 等 559 位作者

原文摘要

We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.

cs.CL · cs.AI · cs.LG

版本更新 · v3arXiv:2508.04189

BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting

Kunlan Xiang, Haomiao Yang, Wenbo Jiang, Haoxin Wang, Shiyue Huang, Shaofeng Li, Yijing Liu, Ji Guo

原文摘要

Multivariate long-term time series forecasting (MLTSF) models are increasingly deployed in critical domains such as climate, finance, and transportation. Despite their growing importance, the security of MLTSF models against backdoor attacks remains entirely unexplored. To bridge this gap, we propose BadTime, the first effective backdoor attack tailored for MLTSF. BadTime can manipulate hundreds of future predictions toward a target pattern by injecting a subtle trigger. BadTime addresses two key challenges that become particularly severe in MLTSF: (i) the rapid dilution of local triggers over long horizons, and (ii) the extreme sparsity of backdoor signals under stealth constraints. To counter dilution, BadTime leverages inter-variable correlations, temporal lags, and data-driven initialization to design a distributed, lag-aware trigger whose influence persists over long-range forecasts. To overcome sparsity, it mixes label-similar and label-dissimilar poisoned samples and adopts a decoupled backdoor training objective that explicitly up-weights the sparse backdoor signal, enabling reliable learning at a poisoning rate as low as 1%. Extensive experiments show that BadTime significantly outperforms the state-of-the-art backdoor attack on time series forecasting by extending the attackable horizon from at most 12 timesteps to 720 timesteps (a 60x improvement) and reducing the MAE on target variables by 57% on average, while changing the average clean forecasting error by less than 1%.

cs.CR

新论文 · v1arXiv:2610.37243

TCM-DiagCommit: A TCM-SD-Derived Benchmark for Evidence-Conditioned Syndrome Selection and Commitment

Erwei Hou, Yue Hu

原文摘要

Traditional Chinese Medicine (TCM) syndrome differentiation is usually evaluated as static final-label selection over complete clinical records. This setting hides three diagnostic behaviors: whether a model distinguishes semantic-neighbor syndrome labels from easy random distractors, whether it updates predictions as evidence fields are revealed, and whether it should commit under uncertainty. We introduce TCM-DiagCommit, a benchmark derived from the public TCM-SD/ZY-BERT resource while retaining its source syndrome labels; it converts 1,834 source cases into 23,842 task rows over 148 syndrome labels. The benchmark combines random, profile-neighbor, and full-vocabulary candidate ladders with staged t1/t2/t3 evidence. It also includes fixed-label tongue/pulse perturbations and insufficient-evidence variants. A benchmark-defined action contract scores commit, acquire, defer, and abstain. Across five zero-shot DirectLLM calibrations, random10 top-1 accuracy is 63.2% to 66.4%, but hard20 falls to 24.7% to 30.3% and full148 to 14.8% to 22.3%; on hard20, WT(all) wrong-terminal commits remain 62.2% to 74.3%. These results show that final-answer accuracy alone is insufficient for diagnostic benchmark evaluation: answer selection, evidence use, and benchmark commitment scoring should be measured separately.

cs.AI

新论文 · v1arXiv:2610.35036

Mapping the Solution-Set Structure of Grokking on Latin Squares

Zihan Gu, Lulu Zhao, Tianyi Ma, Hua Zhang, Wenbo Su, Yanan Cao, Yue Hu

原文摘要

Grokking is a delayed transition from memorisation to generalisation. A network first fits observed examples while remaining near chance on held-out inputs, then generalises abruptly. Prior work has focused mainly on this delay, finding that the network's main loss becomes weight decay after the fitting phase. We name the solution to this optimization problem as the minimum-norm endpoint, and study which tasks make all minimum-norm endpoints generalise from partial observations. Specifically, we model pairwise input tasks as edge colourings of $K_{q,q}$, with Latin colourings as our structured family, and classify each observed instance as all-good, mixed, or no-good by its endpoint set. Furthermore, we prove two contrasting results: (1) Finite-abelian-group families are asymptotically all-good from partial observations; (2) Under a uniform random Latin square, all-good tasks become asymptotically rare for observation-based learners, leaving mixed or no-good behaviour. Moreover, experiments show that relabellings of addition generalise despite their dense polynomial representations. Finally, on tasks of composite order, finite-training results suggest that predictors learn a coarse part of the output before the full label.

cs.LG

版本更新 · v2arXiv:2606.13174

TellOnce: Correcting Coding Agents Once, Improving Their Future Actions

Yujun Zhou, Kehan Guo, Haomin Zhuang, Xiangqi Wang, Yue Huang, Zhenwen Liang, Pin-Yu Chen, Tian Gao 等 11 位作者

原文摘要

Interactive LLM agents increasingly work with users across tasks, yet remembering a previous correction does not ensure that the agent changes its behavior in the future. In a diagnostic constructed from anonymized real-world agent interactions, agents using Mem0 still violate 57.5% of applicable preference checks. We introduce TellOnce, a drop-in personalization layer that turns conversational corrections into persistent, scoped, and revisable behavioral rules without updating the underlying agent model. TellOnce identifies which requirements should persist, determines when they apply, reconciles subsequent feedback with existing rules, and prepares reusable checks when reliable verification is possible. We evaluate whether learned corrections improve future behavior by freezing the learned state and testing on subsequent tasks without additional user corrections. Across three models on ClawArena and MemoryArena, TellOnce achieves the lowest preference violation rate in all six settings, reducing violations relative to PGMem by 19.3-42.3 percentage points on ClawArena and 3.0-22.9 points on MemoryArena, while maintaining broadly comparable task performance. On SWE-Together, TellOnce further improves task quality on new coding tasks by learning from feedback received during earlier tasks. Experiment code is available at https://github.com/YujunZhou/TellOnce_exp, and the deployable skill at https://github.com/YujunZhou/tellonce.

cs.LG · cs.CL

新论文 · v1arXiv:2610.33624HF 社区推荐

RSI Arena: Towards Recursive Self-Improvement with Human Feedback

Yue Huang, Yanbo Wang, Lichi Li, Yuanyuan Chen, Andreas Haupt, Xiaonan Luo, Zheyuan Liu, Jihye Choi 等 18 位作者

原文摘要

Can AI agents autonomously train useful language models and improve them using feedback from users? We introduce RSI Arena, a two-stage study of autonomous post-training as a step toward recursive self-improvement. Ten frontier models act as training agents, each starting from NVIDIA Nemotron 3.5 Lightning 30B-A3B Base. During a six-day first stage, each agent has 1,000 GPU-hours and $300 in API credit on a shared 64-GPU cluster, independently selecting data, implementing training procedures, and choosing checkpoints. We evaluate their models on 20 benchmarks and through blind human evaluations. All ten agents produce working assistants, with the strongest model, trained by GPT-6 Astra, closing a median of 76% of the base-to-Instruct gap across 12 capability benchmarks. Its human-preference rating is also close to NVIDIA Instruct after statistical adjustment for answer length and formatting. In Stage 2, each agent receives the comparison records and votes involving its Stage 1 model and is given three additional days for further training. Using NVIDIA Instruct as a common reference across the two evaluation rounds, we observe an improvement from Stage 1 to Stage 2 in the style-adjusted relative rating of eight of the ten models. We show that benchmark gains were modest, with no clear link to preference gains, while some agents encouraged longer responses and one model showed increased harmful compliance on StrongREJECT. RSI Arena provides an auditable setting for studying how human feedback can guide autonomous model development. It takes a step toward recursive self-improvement with human feedback (RSIHF), in which people help define what improvement means for the AI systems they use.

cs.CL · cs.AI

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-demo.17ACL Anthology · ACL 2026

RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems

Yu Jiang, Wenjie Wang, Yue Huang University of Notre Dame, Yanbo Wang Mohamed bin Zayed University of Artificial Intelligence, Zhenhong Zhou, Xiuying Chen Mohamed bin Zayed University of Artificial Intelligence, Yang Liu Nanyang Technological University, Pin-Yu Chen International Business Machines 等 10 位作者

原文摘要

Large language model (LLM) agents increasingly operate in multi-agent settings where failures emerge from interaction dynamics rather than isolated model errors. We introduce RiskLab, an open-source toolkit for instantiating, probing, and measuring emergent risks in LLM-based multi-agent systems under controlled conditions. Each experiment is defined as a structured topology–environment–protocol–agent–task quintuple, enabling reproducible studies of how communication structure, coordination mechanisms, and incentives shape system-level risks. RiskLab provides flexible communication topologies, swappable interaction protocols, trajectory-grounded evaluation, and extensible registries for risk detectors and agent backends. We demonstrate the toolkit across representative risks, including collusion, resource overreach, semantic drift, and strategic misreporting, and support one-file reproducibility via configuration.

cs.CL · cs.MA

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.74ACL Anthology · ACL 2026

Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents

Haojin Yang, Ai Jian, Yiwei Wang, Xinyue Huang, Weipeng Zhang, Ke Zeng, Xunliang Cai, Jingqing Ruan

原文摘要

Optimizing large language models for industrial sales requires balancing long-term commercial objectives (e.g., conversion rate) with immediate linguistic constraints such as fluency and compliance. Conventional reinforcement learning often merges these heterogeneous goals into a single reward, causing high-magnitude session-level rewards to overwhelm subtler turn-level signals, which leads to unstable training or reward hacking.To address this issue, we propose Dual-Horizon Credit Assignment (DuCA), a framework that disentangles optimization across time scales. Its core, Horizon-Independent Advantage Normalization (HIAN), separately normalizes advantages from turn-level and session-level rewards before fusion, ensuring balanced gradient contributions from both immediate and long-term objectives to the policy update.Extensive experiments with a high-fidelity user simulator show DuCA outperforms the state-of-the-art GRPO baseline, achieving a 6.82% relative improvement in conversion rate, reducing inter-sentence repetition by 82.28%, and lowering identity detection rate by 27.35%, indicating a substantial improvement for an industrial sales scenario that effectively balances the dual demands of strategic performance and naturalistic language generation.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1024ACL Anthology · ACL 2026

LitVISTA: A Benchmark for Narrative Orchestration in Literary Text

Mingzhe Lu, Yiwen Wang, Yanbing Liu Institute of Information Engineering,Chinese Academy of Sciences, Qi You, Chong Liu University of Science and Technology of China, Ruize Qin, Haoyu Dong, Wenyu Zhang Baidu 等 11 位作者

原文摘要

Computational narrative analysis aims to capture rhythm, tension, and emotional dynamics in literary texts. Existing large language models can generate long stories but overly focus on causal coherence, neglecting the complex story arcs and orchestration inherent in human narratives. This suggests a structural misalignment between model- and human-generated narratives.We therefore position narrative analysis as a diagnostic proxy for generation and propose VISTA Space, a high-dimensional framework for narrative orchestration that unifies human and model perspectives while jointly characterizing narrative function and structure in a common space.We further introduce LitVISTA, a structurally annotated benchmark grounded in literary texts, which operationalizes VISTA Space for systematic evaluation of models’ narrative orchestration capabilities. Under an oracle setting with gold event anchors, we evaluate frontier LLMs including GPT, Claude, Grok, and Gemini. Results reveal systematic deficiencies, as current models struggle to jointly capture narrative function and structure and fail to form an integrated global view of literary narrative orchestration. End-to-end analysis further shows that failures are dominated by anchor identification and localization errors. Even advanced thinking modes yield mixed and often limited gains for literary narrative understanding.

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.1089ACL Anthology · ACL 2026

Gradient-Guided Multi-Judge Prompt Optimization

ChenZhuo Zhao, Xinda Wang Peking University, Pu Zhao, Yue Huang, Junting Lu, Ziqian Liu, Qingwei Lin Microsoft Research, Saravan Rajmohan Microsoft 等 9 位作者

原文摘要

Automatic prompt optimization is a practical alternative to fine-tuning for adapting large language models (LLMs), yet existing approaches often trade off signal quality against computational cost. Methods that rely on generative feedback can be informative but expensive to scale, while sampling-based optimization typically requires many evaluations and exhibits high variance. Even loss-driven prompt optimization remains limited by costly segment attribution that scales with prompt length and by overfitting to a single evaluator, which weakens transfer across model families and domains. We propose Gradient-guided Multi-judge Prompt Optimization (GMPO), a scalable framework that improves both efficiency and robustness. GMPO uses a first-order gradient approximation to score segment importance in a continuous masking direction, requiring only one forward and one backward pass. GMPO further employs a generate multi-judge design in which candidate prompt edits are proposed by a generator and selected using cross-entropy losses aggregated from multiple lightweight judge models, reducing evaluator bias and improving generalization. Experiments across math, reasoning, instruction-following evaluation, and safety robustness benchmarks demonstrate consistent gains with substantially lower optimization overhead.

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.1261ACL Anthology · ACL 2026

AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment

Yixuan Wang, Yue Huang East China Normal University, Hong Qian East China Normal University; Shanghai Innovation Institute, Yunzhao Wei, Yifei Ding, Wenkai Wang East China Normal University, Zhi Liu, Zhongjing Huang East China Normal University 等 10 位作者

原文摘要

Creativity has become a core competence in the era of LLMs and human–AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment instruments. Psychometric research recognizes context-based assessment as an effective way to measure creative thinking. However, high-quality expert-designed contexts remain scarce. Existing LLM-based generators often struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking. To address these challenges, we propose AlphaContext, an evolutionary tree-based psychometric context generator for creativity assessment. First, the HyperTree Outline Planner formalizes expert-designed outlining as a rule-guided hypertree and performs top-down hierarchical planning. The MCTS-based Context Generator fills the outline via MCTS to balance global structure and local quality. Then, the Evolutionary Context Optimizer evolves contexts with MAP-Elites by repeatedly updating niche elites to jointly improve diversity and quality. Finally, the Assessment-Guided Evolution Refiner simulates virtual participants with diverse styles and recycles weak contexts for further evolution. Experiments show that AlphaContext yields an average improvement of 8% over competitive methods across 6 quality metrics.

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.1502ACL Anthology · ACL 2026

Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification

Zihan Gu Institute of Information Engineering, Chinese Academy of Sciences, TianYi Zhang University of the Chinese Academy of Sciences, Xinyan Zhang independent, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu Shanghai Jiao Tong University, Tianyi Ma 等 11 位作者

原文摘要

Model editing provides a promising mechanism for updating large language models (LLMs) without expensive retraining. Existing approaches, particularly locate-and-edit methods based on least-squares optimization, aim to introduce targeted knowledge changes while preserving pre-trained behavior. In this work, we show that this objective is fundamentally fragile under standard single-edit evaluation protocols. We first develop a unified theoretical framework that characterizes activation-based editing as a constrained intervention on intermediate representations. Within this framework, we demonstrate that least-squares edits cannot, in general, isolate target updates from unrelated activations, giving rise to unavoidable interference that accumulates with successive edits. Crucially, this degradation can remain undetected in single-edit settings when assessed using conventional success and locality metrics. To expose such hidden instabilities, we introduce an uncertainty-based evaluation protocol that combines structured semantic perturbations with uncertainty quantification based on Sampling with Perturbation for UQ. By measuring edit-induced growth in aleatoric and epistemic uncertainty, our method reveals local knowledge conflicts that are invisible to existing benchmarks. Extensive experiments across multiple models, datasets, and editing algorithms show that both least-squares and other parameter-update-based methods consistently increase post-edit uncertainty. Together, our results suggest that current evaluation practices substantially overestimate the reliability of single-edit model editing, and that uncertainty-based diagnostics are necessary for assessing edit stability.

cs.CL

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