Research Paper Cockpit

Daily Digest - 2026-11-17

Papers first seen in this daily snapshot.

Daily Archives

Quick jump into generated daily digests.

Research Workflow

Latest digest: 2026-11-17.

Papers

58 visible entries

arxiv Score 27.0

WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents

2026-11-13 · Imene Kerboua, Fatemeh Pesaran Zadeh, Xing Han Lù, Weijian Qi, Alexander Miller, Junyi Song, Yunjia Tian, Dongjin Kang, Seyeon Choi, Marzia Nouri, Ewen Gueguen, Matteo Boglioni, Fengyuan Liu, Zeyi Liao, Mengqi Yuan, Yue Li, Alexandre Lacoste, Alexandre Drouin, Spandana Gella, Huan Sun, Gunhee Kim, Siva Reddy

Research Track B · General AI

Web agents powered by large language and vision-language models are increasingly applied to realistic browser work that spans heterogeneous applications, multimodal content, and stateful workflows. However, existing reproducible web-agent benchmarks cover only a small number of web applications drawn from a few softwar…

Review
pending
Role
unreviewed
Read
now
arxiv Score 24.0

Sage S2.1 Flash Technical Report

2026-11-16 · Kun Cai, Haodong Chen, Guangran Cheng, Qingxiu Cheng, Xu Dai, Guanting Dong, Qiming Ge, Lixin Gu, Tao Gui, Honglin Guo, Yuyang Hu, Zixian Huang, Jiajie Jin, Alexander Lam, Jiaqiang Li, Yining Li, Jiahang Lin, Yanjiang Liu, Xinyu Lu, Haijun Lv, Ningsheng Ma, Zerun Ma, Minlong Peng, Jianmin Qian, Huayu Sha, Junlin Shang, Shuo Shen, Qisheng Su, Jiajun Sun, Yanan Sun, Zhichao Sun, Ran Tao, Zhongbo Tian, Guoqiang Wang, Hui Wang, Rui Wang, Yiding Wang, Zhecan Wang, Hao Xiang, Xinchen Xie, Shuhao Xing, Xiaoyu Xing, Wanghan Xu, Xinyu Yang, Yajie Yang, Dingbo Yuan, Yuhang Zang, Hongjie Zhang, Chengfeng Zhao, Haoran Zhao, Penghao Zhao, Ruojun Zhou, Dongsheng Zhu, Yicheng Zou, Qiye Cai, Yifei Cao, Xinmeng Che, Hongji Chen, Jiabei Chen, Jiadong Chen, Jiahao Chen, Jiayi Chen, Xinjie Chen, Yujia Chen, Xin Deng, Yi Dong, Yichen Dong, Wenjie Fu, Jianing Geng, Chenyang Gu, Ding Han, Han Han, Feiyang Hao, Haotan He, Qiushi He, Xufeng He, Xin Hong, Jie Hou, Binze Hu, Yongkang Hu, Zijian Hu, Enfu Huang, Junhao Huang, Changhao Jiang, Huicheng Jiang, Jiazhen Jiang, Shufan Jiang, Wenqing Jing, Jiahao Kuang, Bowen Lai, Bo Li, Qi Li, Qilong Li, Zhuoqun Li, Tianhao Liang, Jiaxiang Liu, Junzhang Liu, Shaofan Liu, Shuainan Liu, Tong Liu, Yi Liu, Ziyu Liu, Zhonghang Lu, Jianwen Luo, Xuan Luo, Yanyi Luo, Huijie Lv, Mingyu Ma, Houcheng Min, Hongjun Mo, Songhao Ni, Chengjun Pan, Qiyuan Peng, Xiaoxuan Peng, Wanying Ren, Runhui Ruan, Jifei Shan, Zixin Shang, Bing Shao, Zhuohui Sheng, Jiayang Shi, Qingyun Shi, Yang Shu, Aierpanjiang Simayi, Sirui Song, Yuxiao Song, Jiahao Sun, Zhe Sun, Wenzhe Tan, Guoxiang Wang, Hanchen Wang, Jie Wang, Pengbo Wang, Qing Wang, Weihang Wang, Xiaotao Wang, Yuhui Wang, Zhekai Wang, Zihan Wang, Zile Wang, Jinke Wu, Liwei Wu, Xuansheng Wu, Yida Wu, Yihao Wu, Yinqi Wu, Yue Wu, Yuhan Wu, Yuwa Wu, Zhiheng Xi, Ying Xiao, Zhide Xie, Caijun Xu, Xingle Xu, Yichen Xu, Yongfeng Xu, Xiaolei Yang, Zhixiong Yang, Jiacheng Yao, Dingcheng Yi, Shihong Yi, Jinhui Yin, Peizhou Yu, Shan Yu, Hao Yuan, Junjie Yuan, Xiongyao Zha, Bo Zhang, Caixian Zhang, Kaicheng Zhang, Pengxiang Zhang, Qiuyinzhe Zhang, Wei Zhang, Xiaoqian Zhang, Xinsen Zhang, Jiyuan Zhao, Shuyu Zhao, Pujun Zheng, Zheyu Zheng, Xiaoxue Zhong, Peiheng Zhou, Xiaohao Zhou, Xinyu Zhou, Fangyi Zhu, Guanru Zhu, Yulun Zhu, Jiabao Zhuang, Pengfei Cao, Zhicheng Dou, Xianpei Han, Ben He, Guoxiu He, Xuanjing Huang, Tao Ji, Yu-Gang Jiang, Dahua Lin, Hongyu Lin, Kang Liu, Yaojie Lu, Le Sun, Ji-Rong Wen, Jun Zhao, Yutao Zhu, Qi Zhang, Bowen Zhou

Research Track B · General AI

We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measureme…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.8

Microfitting: Continual Learning via Cached Test-Time Training

2026-11-15 · Nick Ryan, Peter A. Devine, Ben Sirb, Hannah Sansford, Alex Chiocchi

Research Track A

Continual learning is a promising approach to specialize language models to an organization's private data. However, current methods exhibit a number of drawbacks including catastrophic forgetting, where new training updates overwrite prior knowledge. We present microfitting, which trains and caches a small adapter for…

Review
pending
Role
unreviewed
Read
now
arxiv Score 21.3

ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization

2026-11-16 · Huawei Lin, Jinting Liu, Tongyan Wang, Xuyang Chen, Ruihua Shi, Zhichao Xu, Jiaxin Qin, Guoshenghui Zhao, Baijian Yang, Yingjie Victor Chen, Tan Yu, Weijie Zhao

General AI

Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence. Reinforcement learning (RL) on the final answer cannot correct this, because a guess earns the same reward as reading. We propo…

Review
pending
Role
unreviewed
Read
now
arxiv Score 20.3

Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent

2026-11-16 · Blas Eugenio Vicco Zarate, Miguel Hernán Vicco

Research Track A · General AI

Continual reinforcement learning requires adaptation to changing conditions while preserving performance under previously encountered dynamics. It was investigated whether specialists generated by evolutionary search can provide a reusable memory when combined with environment detection and failure-driven search. The E…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.5

Fuzzy Explainable Continual Hierarchical Reinforcement Learning for Robotic Navigation

2026-11-16 · Peng Qin, Tao Zhao

Research Track A · General AI

Continual robot navigation requires reinforcement learning policies to continuously adapt to new environments while retaining previously acquired knowledge. Meanwhile, explainable reinforcement learning aims to learn meaningful behavioral representations through policy interaction. However, these objectives are inheren…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.3

RESILAGENT: A Three-Pillar Architecture for Cyber-Physical Resilience in Electrical Power and Energy Systems

2026-11-16 · Nikolaos Kekatos, Georgios Koutidis, Konstantinos Antonakopoulos, Stylianos Basagiannis, Sokratis Katsikas, Georgios Kavallieratos, Alexios Lekidis, Tom Nianios, Elpiniki Papageorgiou

General AI

Electrical Power and Energy Systems face hybrid threats that combine cyber intrusions, physical sabotage and climate-driven stress, and routinely outpace today's siloed monitoring stacks. We present RESILAGENT, a concept architecture organised around three operational pillars, Sensing & Data Intelligence, Resilience An…

Review
pending
Role
unreviewed
Read
now
arxiv Score 19.0

AdMem: Expectation-Grounded Procedural Memory for Long-Horizon Task-Solving Agents

2026-11-16 · Runzhe Wang, Huilin Lu, Shengjie Liu, Li Dong, Zhihuai Zhu

Research Track A · General AI

An agent that carries memory across tasks is only as good as the entries it keeps. We begin from an observation that is easy to reproduce and uncomfortable for the field: naively accumulating cross-task experience can make an agent \emph{worse} than one with no memory at all. On AgentBoard, a workflow-induction memory …

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.3

Out of Sight, Into Memory: Compact Visual Latents Retain Local Evidence in Ultra-High-Resolution Remote Sensing

2026-11-16 · Meng Tang, Siyuan Du, Yuxin Liu, Shuaishuai Cao, Di Wang, Haonan Guo

Research Track A · General AI

Question answering over ultra-high-resolution (UHR) remote sensing scenes poses a tension for multimodal large language models: global overviews obscure small objects and local attributes, whereas detailed crops consume substantial context. Compressing inspected crops into short sequences of continuous visual latents o…

Review
pending
Role
unreviewed
Read
now
arxiv Score 18.3

SciResearch-Eval: Evaluating Scientific Judgment in Autonomous Experimental Agents

2026-11-16 · Brian T. Weston, Alondra Torres Contreras, Aldair E. Gongora

General AI

We introduce SciResearch-Eval, an interactive benchmark of scientific judgment built on a standard laboratory problem: measuring a material's thermal properties by heating it and fitting a heat-conduction simulator. An agent designs its own experiments, uses a supplied simulator that may be under-resolved or physically…

Review
pending
Role
unreviewed
Read
now
huggingface Score 17.5

DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images

2026-11-16 · Emilio Ferrara

General AI

Can a vision-language model look at a picture of a chain reaction and tell what will happen? Recent multimodal models describe scenes fluently and solve textbook physics problems, which suggests they should also predict how a scene of ramps, ledges, pendulums, seesaws and dominoes plays out once a ball is pushed. We te…

Review
pending
Role
unreviewed
Read
now
huggingface Score 17.5

InclusionMed: Benchmarking AI for Inclusive Healthcare

2026-11-16 · The InclusionMed Collaboration

General AI

Advancing medical AI for inclusive healthcare requires evaluation across diverse healthcare roles, tasks, and care settings, but benchmark coverage remains uneven. We introduce InclusionMed, an open medical AI evaluation initiative for inclusive healthcare. The InclusionMed Atlas organizes benchmarks across three healt…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

Conflict-Aware Multi-Teacher On-Policy Distillation in Aligned Action Spaces for Cross-Game Generalization

2026-11-16 · Jing Yi, Cehao Yang, Hualei Zhang, Haitao Li

Research Track A · General AI

Zero-shot cross-game generalization aims to consolidate accessible source-game experts into a single vision-language model (VLM) that controls unseen games from raw pixels without target-game parameter updates. While multi-teacher on-policy distillation (MOPD) mitigates offline exposure bias and single-game reinforceme…

Review
pending
Role
unreviewed
Read
now
arxiv Score 17.0

Instant Weight-Space Consolidation for Long-Term Memory in LLMs

2026-11-16 · Manan Suri, Dinesh Manocha

Research Track A · General AI

Agentic memory systems give LLMs persistent memory by extracting experience into text and retrieving it at query time, but the model itself does not evolve: however many interactions it has had, it starts each query the same. Extraction errors compound, implicit cross-session patterns that no single fragment states can…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.8

Incremental Learning of Vision-Language Models via Task Subspace Projection and Dynamic LoRA

2026-11-14 · Hao Fu, Qian Feng, Hanbin Zhao, Jiahua Dong, Xu Tan, Lina Wei, Chao Zhang, Hui Qian

Research Track A · General AI

Recent pre-trained vision-language models often encounter a Multi-Domain Task-Incremental Learning (MTIL) scenario in practice, where a set of classes of multi-modal tasks arrive incrementally. Due to privacy concerns and memory constraints, MTIL with pre-trained models encounters forgetting of knowledge from old tasks…

Review
pending
Role
unreviewed
Read
now
arxiv Score 16.8

Protecting Safety during Reasoning Training with Low-Rank Fisher Regularisation

2026-11-15 · Neel Rajani, Ivan Titov

Research Track A · General AI

Large language models are trained to have safety guardrails, but these can be compromised while fine-tuning for new capabilities, such as reasoning. One way to mitigate this degradation is to modify the fine-tuning objective to preserve safety behaviour, but doing so effectively and efficiently remains challenging. We …

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.5

Replay-Augmented Regularisation for Class-Incremental Network Intrusion Detection: A Three-Dataset Evaluation of EWC and LwF

2026-11-16 · Mohammed Fackruddin Tusher, Muhammad Iqbal Hossain

Research Track A

As new attack categories emerge, network intrusion detection models need to be updated; however, when fine-tuned sequentially on new classes, previous classes are forgotten, resulting in catastrophic for- getting. The three public datasets we use are UNSW-NB15, ToN-IoT and CIC-IDS2017, and for these datasets, our class…

Review
pending
Role
unreviewed
Read
now
arxiv Score 15.3

Learning to Reason with Predictive Gains for Generative Recommendation

2026-11-16 · Zhuoyang Li, Teng Shi, Jiakai Tang, Weijie Yu, Guofu Xie, Xiao Zhang, Lei Kou, Yang Yu, Lei Shen, Xin Chen, Bing Wang, Xiaoyi Zeng, Jun Xu

General AI

Reasoning-enhanced generative recommendation (GR) has attracted increasing attention for leveraging the reasoning capabilities of large language models (LLMs) to improve next-item prediction. However, existing methods primarily optimize reasoning through Group Relative Policy Optimization (GRPO) with rule-based rewards…

Review
pending
Role
unreviewed
Read
now
huggingface Score 14.8

Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning

2026-11-15 · Xuan Gong, Hanbo Huang, Hao Zheng, Yiran Zhang, Wenbin Dai, Weishu Zhao, Shiyu Liang

General AI

Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Existing methods either re-inject vision at inference or train policies for stronger grounding, but where to intervene relies on perception heur…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.3

BLIP-Live: Balancing Timeliness & Firing Precision in Proactive Streaming Video Agents

2026-11-16 · Kanchana Ranasinghe, Honglu Zhou, Dominick Reilly, Le Xue, Shusheng Yang, Juan Carlos Niebles, Silvio Savarese, Ran Xu

General AI

Streaming video understanding is becoming increasingly important for real-world interactive systems. Such systems must be proactive for natural and useful human interaction: they should respond as soon as sufficient evidence becomes available while avoiding premature, redundant, or incorrect responses. We present BLIP-…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.3

Evaluating Cultural Reasoning and Robustness in LLMs for Spanish Political Discourse

2026-11-16 · Jorge Valverde-Rebaza, Nathan Garcia-Larios, Karime Ruvalcaba-Perez, Alejandro Rendon, Santiago Sanchez-Ballesteros, Alejandro Martin del Campo

General AI

Large language models (LLMs) are increasingly used to interpret, generate, and mediate public-facing language, which makes their reliability especially consequential in politically sensitive settings. Although sentiment analysis is a common task in this area, affective meaning in social media discourse is often conveye…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.3

Living Context Graphs: Continual Semantic Learning for Enterprise Data Reasoning

2026-11-16 · Varun Agrawal, Ayush Srivastava, Eshan Gujar, Kaushal Kumar, Ayush Gupta

General AI

Enterprise AI can now perform analytics, reporting, and data-driven workflows, yet the data foundations it relies on remain hard to operationalize: business meaning, relationships, metric definitions, and reporting conventions are absent from database schemas and scattered across undocumented systems and tribal knowled…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.3

ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters

2026-11-16 · Ruixi Yu, Dairu Liu, Xuchuan Chen, Zekun Qi, Zekai Li, Zhuo Cao, Luyang Niu, Yingsheng Zhang, Sikai Liang, Ke Fan, He Wang, Li Yi

General AI

Frontier Vision-Language Models (VLMs) such as GPT-6 Astra have demonstrated remarkable capabilities in robot control, suggesting that broad pretraining provides knowledge valuable for physical action. Yet most Vision-Language-Action (VLA) policies still rely on much smaller VLM backbones, leaving this potential largel…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.3

When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents

2026-11-16 · Zeynab Anbiaee, Sajjad Dadkhah, Ali A. Ghorbani

General AI

Large language model (LLM) applications increasingly act as agents that select and invoke external tools. The Model Context Protocol (MCP) standardizes this interaction by allowing clients to compose tools advertised by multiple servers. However, tool metadata used for discovery and selection is not, by itself, necessa…

Review
pending
Role
unreviewed
Read
now
arxiv Score 14.0

Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination

2026-11-13 · Mohamed Aghzal, Mor Geva, Gregory J. Stein, Ziyu Yao

Research Track B · General AI

Mechanistic Interpretability (MI) has made significant progress in explaining the internal computations of Large Language Models (LLMs); however, these advances have yet to demonstrate comparable success in explaining the decision-making processes of LLM-based agents. This paper examines the challenges MI tools face wh…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.8

BadGCL: Towards Persistent Backdoor Attack on Graph Continual Learning Systems

2026-11-14 · Dong Li, Yufei Han, Xintao Wu, Xujiang Zhao, Wei Cheng, Chen Zhao

Research Track A · General AI

Backdoor attacks pose a persistent security threat to machine learning systems, yet their behavior under graph continual learning (GCL) remains underexplored. Conventional graph backdoor attacks often lose effectiveness as models are updated across successive tasks, creating the impression that continual updates natura…

Review
pending
Role
unreviewed
Read
now
huggingface Score 13.5

Accelerate Bench: Evaluating Agents for Application-Level Program Optimization

2026-11-16 · Bowen Liu, Yuhan Li, Nuo Chen, Weile Luo, Miao Peng, Qintong Zhang, Qifan Zhang, Jia Li, Ziqi Gao, Lydell Huang

General AI

Application optimization requires coding agents to discover useful changes and coordinate them across a complete program while preserving the required computation. We introduce Accelerate Bench, a benchmark of 32 CPU optimization tasks adapted from scientific applications and supercomputing competitions. Each task prov…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

Latent Lattice Language Models

2026-11-16 · Shivam Duggal, Zongze Wu, William T. Freeman, Antonio Torralba, Richard Zhang, Eli Shechtman

General AI

Language models typically increase per-token computation through deeper or looped layers and latent reasoning steps, while richer residual connections improve information flow across layers. We instead increase computational capacity: the number of active computational states a model maintains. We introduce the Lattice…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

Procedure without Judgment: What Small Language Models Learn under an Exact Verifier

2026-11-16 · Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R., Arun Prakash, S. Senthilkumar

General AI

When an authorization policy blocks an agent's tool call, the audit log should name the facts that forced the decision and nothing more. For an executable policy over an enumerable context space this minimal sufficient reason can be computed exactly, so an explanation is scored against ground truth rather than a proxy …

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.3

Wildfire-SSR: Geolocation-Aware Multimodal Fusion for Structure-Level Wildfire Risk Assessment

2026-11-16 · Yu-Hsuan Ho, Yiming Xiao, Hao-En Lai, Ali Mostafavi, Samuel D. Brody

General AI

Structure-level wildfire vulnerability assessment is critical for reducing losses in wildland-urban interface communities, yet existing methods often fail to combine parcel-scale ignition pathways with community-scale geographic coverage. This study introduces Wildfire-SSR (Satellite and Street-view for wildfire Risk),…

Review
pending
Role
unreviewed
Read
now
arxiv Score 13.0

Beveridge: Open Weight System One Decision Models with Calibrated Probabilities

2026-10-17 · Sathiskumar Jothi

Research Track B · General AI

Many production systems need a model to make a narrow decision about a document (route a ticket, check a limit, refuse a request, pick the next step of a browser agent) rather than to write text about it. We present Beveridge, a family of open weight System One decision models that take a document and up to 15 typed qu…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.8

SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

2026-11-15 · Xinping Lei, Minghao Liu, Ruijie Zhu, Xiaohui Hu, Xingqiao Li, Ao Zhang, Wenhao Chai, Han Li, Tao Wang, Jingyuan Zhang, Enduo Zhao, Yunfeng Shi, Yiming Liang, Zetao Yang, Xingjian Wang, Yifan Yao, Xinkai Ma, Yingru Li, Tianhan Yang, Huan Zhou, Weiran Shi, Shen Yan, Jiaheng Liu, Stephen Huang, Eli Cheung, Weihao Xuan

General AI

A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12 application domains. Each assignment pl…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.3

Detection-Efficient Watermarking for Vision--Language Agents via Risk-Constrained Strength Allocation

2026-11-16 · Dumindu Samaraweera, Prashant Shekhar

General AI

Vision--language agents generate descriptions, decisions, and instructions that may be reused by users, downstream agents, and automated workflows, creating a need for provenance mechanisms that support content authenticity and post-deployment auditing without unnecessarily degrading response quality. We present a risk…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.3

FaceJev: Direct Visual Decisions for Face Forgery Detection

2026-11-16 · Siran Peng, Tianshuo Zhang, Yibo Xue, Ajian Liu, Haoyuan Zhang, Weisong Zhao, Shuhuan Chen, Xiangyu Zhu, Zhen Lei

General AI

Face forgery detection methods often perform well on seen manipulations but generalize poorly to unseen ones. Multimodal Large Language Models (MLLMs) can recognize facial parts and assess their visual plausibility. Existing MLLM-based methods typically express these judgments through textual explanations, but seldom t…

Review
pending
Role
unreviewed
Read
now
arxiv Score 12.3

UNITE: Consolidating Embodied VLM Specialists via Shared-Anchor One-Bit Factorization

2026-11-16 · Tao Tao, Anke Tang, Enneng Yang, Zhi Hou, Xiaogang Wang, Dacheng Tao

General AI

Embodied capabilities such as visual grounding, spatial reasoning, navigation, and driving understanding are often developed in separate vision-language specialists fine-tuned from a common pretrained model.Deploying the specialists separately multiplies storage, whereas merging them into one dense model forces conflic…

Review
pending
Role
unreviewed
Read
now
huggingface Score 12.0

OutfitterBench: Evaluating LLM Agents on Long-Horizon Resource Allocation and Commitment Coordination

2026-11-13 · Jie Huang, Yuecheng Hong, Yao Chen, Shengding Jiao, Xudong Liu, Qiang Ye

General AI

In many long-horizon settings, an agent's own choices create future constraints: committing finite capacity establishes future obligations and forecloses later opportunities. Sustaining performance therefore requires both keeping evolving plans feasible and comparing the value of resource allocations with the alternati…

Review
pending
Role
unreviewed
Read
now
huggingface Score 11.5

A Reinforcement Learning Method to Navigate SMEFT Operator Space

2026-11-16 · Jacky Kumar

General AI

In particle physics, discrepancies between experimental measurements and Standard Model (SM) predictions are commonly interpreted within new theoretical models. In this context, the Standard Model Effective Field Theory (SMEFT) provides a general framework encompassing a broad class of models. However, exploring the en…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 11.5

From Joint Risk to Decision Invariance: Decision-Preserving Regularization for Exemplar-Free Class-Incremental Learning

2026-11-16 · Qi Zhu, Ziang Gan, Wanting Zhang, Libao Zhang

Research Track A

Exemplar-free continual learning seeks to minimize joint risk over all seen tasks, yet historical data are unavailable for direct optimization. We observe that, for classification, preserving the model's decisions on previously learned classes helps retain old knowledge. This motivates Decision-Preserving Regularizatio…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 11.3

How VLMs Plan What's Next

2026-11-16 · Rohit Gandikota, Arnab Sen Sharma, Adam Belfki, David Bau

General AI

When a vision-language model describes an image, it names one object at a time and it rarely repeats itself, yet how the model plans this order is far from obvious. We characterize the mechanism a VLM uses to decide where to look before it looks. The mechanism has four main parts. First, binding heads match the relevan…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 11.3

Learning What Pairs Miss for Higher-Order Multimodal Alignment

2026-11-16 · Kunyu Zhang, Shenghui Feng, Xiangjie Shi, Zeqing Wang, Yingxu Wang

General AI

Contrastive learning beyond two modalities now scores the whole tuple with multilinear products, volumes, and fusion heads, critics that can represent the joint distribution. In practice these critics still behave like bags of pairs. Their negatives break at least two of the three pairs, a single pairwise check rejects…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 11.3

Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests

2026-11-16 · Arunkumar V

General AI

Language models increasingly write the explanations people receive when a rule system denies their request. If several rules deny the request independently, an explanation can name a true reason and still leave the person denied after they fix it. We call the missing property recourse validity: changing what the explan…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 10.8

Continuation-Guided LLM Evolution of Program Policies and Goal Compilers in Craftax

2026-11-14 · Víctor Gallego

General AI

Coding agents can synthesize and optimize code-based policies from simulator feedback, allowing the resulting program to act with zero inference model calls. But for long horizon tasks, two challenges arise: local improvements can hurt final success and switching to a new objective requires another expensive synthesis …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.6

EndoComparer: Comparative Surgical Video Question Answering with Pseudo-Siamese Visual Adaptation and Perceive-then-Compare Reasoning

2026-11-14 · Shi Li, Lalith Sharan, Joël L. Lavanchy, Kun Yuan, Lorenzo Arboit, Nabani Banik, Elif Yazici, Maria Vannucci, Vinkle Srivastav, Pietro Mascagni, Nicolas Padoy

General AI

Purpose: Surgical training benefits from explicit comparison between cases: in patient condition, in technique and in skill proficiency. Surgical vision-language models (VLMs) offer a promising and flexible interface for this purpose. Yet current VLMs typically see one video at a time, and they often fall short when as…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.3

Generative AI and the Crisis of Higher Education Assessments: Examining 'AI-Proofing' Strategies for College-Level Assessments

2026-11-16 · Bonam Mingole, Davis Yadav, Hui Min Lee, S. Shyam Sundar, Amulya Yadav

General AI

Higher education is confronting an academic-integrity challenge unlike any in its history. Students can now outsource homework, take-home assignments, and online examinations to large language models (LLMs) that complete them in seconds. Existing research on evaluating LLM performance on academic assessments has focuse…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 10.3

Share your Screen and Talk to Gemini: How Young Learners Interact with Multimodal GenAI While Solving Scratch Tasks

2026-11-16 · Sven Jacobs, Lukas Berning, Natalie Kiesler

General AI

Children using Scratch to learn programming can struggle with text-heavy, lengthy explanations and hints during debugging. Verbal interactions based on screen sharing or camera data may be an interesting alternative for supporting learners. We therefore explore the quality, use, and perceptions of fifth- and sixth-grad…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 9.5

LynnReal-Hand: Unlocking World Interaction with Hand Control

2026-11-16 · Shaohao Rui, Chaoyang Zhang, Xiaofeng Mao, Weijie Ma

General AI

Interactive video world models enable exploration through text and camera controls, yet direct object interaction requires finer control. Hands provide a natural interface, but translating continuous hand movements into coherent visual responses remains challenging because of complex hand-object dynamics and demanding …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.3

Incentive Alignment for Electricity Data Assets in China: A Blockchain-Enabled Contribution-Credit Framework

2026-11-16 · Jiazheng Zhang, Shouwei Li, Yutian Deng, Wei Wei, John Cartlidge

General AI

Modern electricity markets increasingly rely on reported operational contributions to allocate incentives, recognise cooperation, and coordinate activities across multiple organisations. However, supporting evidence for many reported contributions becomes available only after subsequent metering, dispatch, settlement, …

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.3

Optimistic Verifiers Get Hacked: Reward Hacking Under an Exact Process Oracle

2026-11-16 · Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R., Arun Prakash, S. Senthilkumar

General AI

Reinforcement learning from verifiable rewards inherits whatever its verifier gets wrong. Outside mathematics and code the verifier is a proxy, a rubric, a learned judge or a hand-written checker, and its distance from the true objective is never measured, so a rising reward cannot be told apart from a hack. We build a…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 9.3

Replicating and Extending Weight-Space Programming: Frontier LLMs Compile Programs into Weights and Read Input Layers

2026-11-16 · Roksana Goworek, Alexander Hickey, Federico Nanni, Martin O'Reilly

General AI

Researchers at MIT recently reported that GPT-6 Astra, a frontier large language model (LLM), can write the weights of small neural networks directly in a single reply, and can read the raw weights of small networks to say what they were trained to do. In a three-day sprint, we replicated and extended these results. Ou…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.6

Drift-Conditioned Structural Replay for Continual Cardiac Ultrasound Segmentation

2026-11-15 · Zahid Ullah, Jaeyoon Seo, Jihie Kim

General AI

Conventional experience replay typically applies fixed preservation constraints to historical exemplars, overlooking variations in how learned representations, predictions, and anatomical structures change during sequential training. To address this limitation, we propose Drift-Conditioned Structural Replay Loss (DCSRL…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.3

A2A-UAV: A Multimodal Air-to-Air Dataset for UAV Detection and Identification

2026-11-16 · Hongtao Liang, Yiyao Wan, Kezhi Zhu, Jiayi Zhang, Zequn Jiang, Ziyu Zhou, Jiahuan Ji, Fuhui Zhou, Qihui Wu

General AI

The rapid growth of unmanned aerial vehicles (UAVs) in low-altitude airspace increases the risk of unauthorized intrusions, making reliable detection and identification of non-cooperative UAVs essential for low-altitude airspace safety. However, the existing public UAV datasets are mostly acquired from fixed ground-bas…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 8.3

What Makes a Good Move? Learning to Act from Experience in Visual Worlds

2026-11-16 · Cehao Yang, Ziyi He, Jing Yi, Jian Guo, Hui Xiong

General AI

Learning visual policies requires turning interaction experience into guidance for individual decisions. Trajectory outcomes obscure action quality, while unguided exploration can revisit familiar situations. We present \textsc{LightAct}, an experience-learning framework that connects skill-guided exploration with poli…

Review
pending
Role
unreviewed
Read
soon
arxiv Score 7.3

Surprise-Gated Memory for Live Speaker Diarization

2026-11-16 · Louis Mouchon, Alexis Lainault

General AI

We transpose the Surprise-Gated Memory recipe, a frozen encoder plus a calibrated novelty signal that gates a one-shot episodic store consolidated by periodic replay, from continual visual learning to live speaker diarization. The moment-to-moment question a streaming diarizer must answer, whether an arriving voice bel…

Review
pending
Role
unreviewed
Read
later
arxiv Score 7.3

Trustworthy Numerical Software in the Age of AI: What Would Turing Do?

2026-11-16 · Kimon Fountoulakis, Maksim Melnichenko, Muhammad Fetrat Qharabagh, Georgios Alexandros Georgantzas, George Spyrou, Oleg Balabanov, Vasileios Georgiou, Riley Murray, Michael W. Mahoney

General AI

AI coding agents can now produce numerical software faster than human experts can review it, raising serious concerns about usability and reliability. These and other AI tools are already transforming mathematics and software, and they will soon transform mathematical software. These concerns motivated us to assess AI-…

Review
pending
Role
unreviewed
Read
later
huggingface Score 7.0

Termination Lag: Coding Agents Solve Early but Stop Late

2026-11-11 · Musa Cim, Burak Topcu, Mahmut Taylan Kandemir

General AI

Coding agents can solve a task well before they stop working on it. We characterize termination lag--the number of steps between an agent's first correct patch and the end of its run--across five models, two agent frameworks, and three SWE-bench datasets by recording and testing every distinct repository patch generate…

Review
pending
Role
unreviewed
Read
later
huggingface Score 6.8

JEPA4R: Embodied JEPA World Models with 4D Point Planning

2026-11-15 · Jiarui Dong, Zhiheng Liang, Yanjun Li, Zeyu Zhang, Heejeong Nam, Haoyu Chen, Hao Tang

General AI

Joint-embedding predictive architecture (JEPA) world models predict future embeddings instead of pixels and plan in latent space. Two challenges remain: 2D images leave the metric geometry that manipulation acts on implicit and entangled with appearance, and what these models imagine stays hidden, as they are mostly ju…

Review
pending
Role
unreviewed
Read
later
huggingface Score 6.0

Correcting Persistent Failures in Point-Cloud Grasping Policies using Human Demonstrations in Virtual Reality

2026-11-13 · Achyuthan Unni Krishnan, Karthik Rengarajan, Bharath Narasimhan, Chris von Csefalvay

General AI

Robots in homes, warehouses and farms must pick up objects they have never seen, usually without a 3D model or a category label. A grasping policy that works directly on the point cloud from a depth sensor needs only the geometry the robot observes, so it applies to any new object. Offline grasp generators such as Cont…

Review
pending
Role
unreviewed
Read
later
huggingface Score 5.4

BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design

2026-11-06 · Dayou Du, Woon Yee Ng, Guangming Sheng, Nick Lau, Jianyi Cheng, Luo Mai

General AI

The key-value (KV) cache dominates memory capacity and bandwidth in long-context LLM serving. While 4-bit microscaling formats (NVFP4, MXFP4) shrink the cache and run attention on FP4 Tensor Cores, a fundamental gap remains between algorithmic quantization and system-aware acceleration: existing FP4 KV systems use vani…

Review
pending
Role
unreviewed
Read
later