arxiv
Score 35.8
2026-08-12 · Zhixin Zhang, Xinke Jiang, Zhibang Yang, Weixuan Xu, Guohong Qiu, Xu Chu, Junfeng Zhao, Yasha Wang
General AI
Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical capability in such settings is reflection: assessing trajectory progress, identifying missing evidence and unreliable intermediate states, and deciding whether to continue,…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 26.8
2026-08-11 · Muxin Fu, Yifan Zhang, Wentao Zhang, Fangming Guo, Qian Chen, Guibin Zhang, Shuicheng Yan, Bo An
General AI
Streaming video understanding requires multimodal large language models (MLLMs) to preserve relevant evidence from continuously evolving streams under strict causality and bounded memory. Yet existing paradigms remain limited: model-based methods require intrusive backbone updates, while memory-based methods expend sub…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 23.8
2026-08-12 · Yan Deng, Fei Xu
General AI
Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it has reached a navigation goal under partial observability. Although recent VLA models offer a promising perception-to-action paradigm, adapting them to aerial navigation …
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 23.0
2026-08-12 · Hojun Choi, Jaeyo Shin, Suin Lee, Hyunjung Shim
General AI
Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet existing approaches remain confined to a text-only paradigm, despite the inherently multimodal nature of real-world contexts. We thus introduce MBA-Bench, the first multimodal benchmark for training and eval…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 20.8
2026-08-12 · Weihao Bo, Shan Zhang, Yanpeng Sun, Jie Liu, Yongke Yao, Jinhao Du, Wei He, Kai Zou, Zechao Li, Jingdong Wang
General AI
Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration. For example, OpenAI Prism is a free workspace for scientific writing and collaboration. One important feature in Prism is turning scientific diagrams directly into LaTeX TikZ code. In this paper, we build…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 20.0
2026-08-12 · Tieliang Gong, Zhongbo Zhang, Wen Wen, Yong-Jin Liu
Research Track A · General AI
Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting. Yet its generalization behavior is shaped by two coupled effects that existing analyses fold into a single hypo…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 19.8
2026-08-12 · Nicholas E. Kyrkewood
Research Track A · General AI
Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-inspired compression…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 18.8
2026-08-12 · Simon Yu, Nicholas Tomlin, Marwa Abdulhai, Ximing Lu, Derek Chong, Abe Hou, Dilara Soylu, Sergey Levine, Christopher D. Manning, Weiyan Shi
General AI
Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically fails to generalize, and trace the failure to simulator collapse: because the simulator LLM is mode-collapsed, an LLM policy trained against …
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 18.8
2026-08-12 · Ankita Rajaram Naik, Anupama Murthi, Benjamin Elder, Siyu Huo, Raavi Gupta, Abhinav Jain, Praveen Venkateswaran, Abdulhamid Adebayo, Danish Contractor
General AI
Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\textbf{V}aluating \textbf{A}PI and \textbf{K}nowledge \textbf{R}etrieval \textbf{A}gents), a benchmark of over $8{,}000$ executable …
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 18.0
2026-08-11 · Kushal Chakrabarti
Research Track A · General AI
Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale. We trace this to imperfect recall: appending an instruction is always cheap, but once an instruction's rationale is gone, deleting it without risking a correct…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 17.8
2026-08-12 · Aman Tyagi, Hemanth Boinpally, Jonathan Chen, Douglas Gebert, Steven Hickson
General AI
Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield dr…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 17.8
2026-08-12 · Byungoh Ko, Jinyoung Park, Jongha Kim, Jeehye Na, Jaewon Cho, Hyunwoo J. Kim
General AI
Multimodal large language models (MLLMs) have made rapid progress, yet they still exhibit object hallucination, generating plausible but incorrect descriptions that are inconsistent with the visual input. Direct Preference Optimization (DPO) mitigates this by training models to prefer non-hallucinated responses over ha…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 17.4
2026-08-07 · Guiyu Zhao, Longteng Guo, Yanghong Mei, Zilin Zhu, Yu Zhang, Bin Cao, Mingming Yu, Xingjian He, Jie Jiang, Jing Liu
Research Track A · General AI
While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially observable and long-horizon tasks. When restricted to a single wrist-mounted camera, they inevitably suffer from perception forgetting as objects exit the field of view, an…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 16.8
2026-08-12 · Chuyue Li, Jinpeng Yu, Haozhe Wang, Tian Xueyun, Zhijing Zhang, Bingnan Li, Shuqi Gu, Kan Ren, Jiaming Liu, Ruihua Hua
General AI
Creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key challenge is the absence of a structured video representation that is both faithful to film content and directly usable for agentic reasoning and manipulation. To address t…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 15.8
2026-08-12 · Saman Marandi, Yu-Shu Hu, Mohammad Modarres
General AI
Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically relies on expert interpretation of technical documentation, limiting scalability for complex systems. This study presents …
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 14.8
2026-08-12 · Dehui Gao, Zhixian Zhao, Zhennan Lin, Yujie Liao, Yuhang Dai, Yike Zhu, Longshuai Xiao, Hui Bu, Xin Xu, Xie Chen, Shuai Wang, Liumeng Xue, Zhonghua Fu, Jun Du, Eng-Siong Chng, Jun Zhou, Lei Xie
General AI
Recent advances in large language models (LLMs) and multimodal LLMs (MLLMs) have created new opportunities for wearable speech interfaces, with smart glasses providing an egocentric platform for continuous audio sensing and assistance. However, speech recognition and understanding in this setting remain challenging bec…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 14.0
2026-08-12 · Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung
Research Track A · General AI
Copying short-term memory (STM) into a slower store can preserve state across a context boundary, but persistence alone does not ensure that the retained state influences subsequent memory access. We test this distinction in a Phasor Memory Network (PMNet) using Consolidator, a shared slot-local operator that transform…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 13.8
2026-08-12 · Cheng Qian, Wenting Zhao, Liangwei Yang, Heng Wang, Jielin Qiu, Heng Ji, Silvio Savarese, Huan Wang, Shelby Heinecke
General AI
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods. In this paper, we ask whether such transfer can instead occur at test time. We study strong-to-weak scaffo…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 13.8
2026-08-12 · Zhongbin Guo, Jiahao Xie, Dongling Xiao, Qianle Wang, Ruiqi Lu, Xiaomin He, Wanxuan Sun, Cheng Yang
General AI
While Multimodal Large Language Models (MLLMs) have achieved remarkable progress, visual understanding and generation are typically treated as divergent objectives. Existing unified frameworks often rely on discrete visual tokenization or diffusion objectives whose generative targets differ from the continuous represen…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 13.4
2026-08-08 · Yingpeng Ma, Jianhao Yan, Bei Shi, Ka Hou Kam, Runnan Wang, Xuebo Liu, Yulong Chen, Yue Zhang, Derek F. Wong
General AI
The rapid advancement of Large Language Models (LLMs) is revolutionizing AI for Games by enabling open-ended and fluid interactive storytelling. However, existing research has largely overlooked the critical challenge of maintaining long-horizon logical consistency and narrative integrity against unconstrained user int…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 13.4
2026-08-08 · Jiayue Jin, Jingwei Zhang, Chen Wang, Jing Liu, Longteng Guo
General AI
Multimodal expansion of large language models (LLMs) enables new perceptual capabilities but often compromises the language intelligence acquired during pretraining. In this work, we investigate this phenomenon from the perspective of internal adaptation dynamics and discover that neurons in pretrained LLMs exhibit het…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 13.0
2026-07-19 · Igor Itkin
General AI
Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase behaviour, stylised facts, and scaling with the number of agents N, not the cognition of any single agent. We turn a statistical-physics observation into a method: repl…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 12.8
2026-08-11 · Yueke Zhang, Zihan Fang, Kevin Leach, Yu Huang
Research Track A · General AI
Code large language models (LLMs) can generate syntactically plausible programs that nevertheless violate hidden semantic constraints. Existing execution-feedback training methods identify whether a completed program fails, but provide limited supervision about how a correct solution should be organized. We introduce G…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 12.8
2026-08-12 · Shivali Dalmia, Sumukha Thoppanahalli, Mohammadreza Sediqin, Abhishek Mukherji
General AI
Enterprise guideline documents are heterogeneous and multimodal, combining narrative text, complex tables, and embedded images. Existing LLM and VLM systems face hallucinated content, table structure degradation, and lack governed workflows extending beyond extraction to validation and artifact generation. This leaves …
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 12.2
2026-08-10 · Qingfeng Zhang, Yuanxiong Guo, Yanmin Gong
General AI
Deploying large language models (LLMs) for decision support in emergency departments (EDs) faces two major challenges: privacy risks of transmitting patient data to closed-source commercial LLMs and the lack of systematic evaluation of fine-tuning strategies for locally deployable open-source small language models (SLM…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 12.0
2026-08-11 · Peidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Xiaocui Yang, Shi Feng, Yuqing Yang, Dongsheng Li
General AI
Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the model. While supervised fine-tuning and reinforcement learning can adapt agents to new environments, t…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.8
2026-08-11 · Sanidhya Vijayvargiya, Rahul Lokesh
General AI
Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather than expressing uncertainty. Existing detection methods fail to provide actionable, real-time correction as they either do not localize the …
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.8
2026-08-11 · Carlos Zamora, Hiram Zuniga, Ulises Orozco-Rosas, Kenia Picos
General AI
Leukemia cell image classification is challenged by real-world domain shifts from acquisition, staining, illumination, and site protocols, causing single-dataset models to generalize poorly in real clinical scenarios. This work presents a robust framework for leukemia classification across multiple heterogeneous datase…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.8
2026-08-12 · Junliang Liu, Ruoyu Li, Wenxin Tang, Jingyu Xiao, Zhenyu Liu, Jingheng Xu, Laizhong Cui
General AI
LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design exposes two sequential control points to untrusted publishers: a static skill may steer an otherwise correct task onto an unnecessarily costly tra…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.8
2026-08-12 · Yusuf Pisan
General AI
An effective large language model (LLM) tutor must often decline to give an answer it could easily produce. In a randomized study, students who used an unguarded chatbot scored higher while practicing but lower on a later test taken without it, whereas a Socratically guarded version of the same model kept the practice …
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 11.0
2026-07-20 · Marjan Moodi, Xuankang Zhu, Fernando De Mesentier Silva, Harold Chaput, Mohammad Reza Taesiri
General AI
World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe dominates across environments. This makes it an ideal testbed for AI coding agents acting as autonomous researchers--a setting in which the improvement direction is not spec…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 11.0
2026-08-01 · Yunhao Chen, Xin Wang, Yixu Wang, Yi Liu, Jie Li, Yan Teng, Xingjun Ma, Xia Hu, Yu-Gang Jiang
General AI
AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon workflows. Current safety benchmarks often fai…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 11.0
2026-08-12 · Zepeng Wang, Jiagao Hu, Fuhao Li, Yuxuan Chen, Fei Wang, Daiguo Zhou
General AI
Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks. Although single-image reflection removal has been extensively studied, video reflection removal remains largely underexplored due to the lack of paired video data, temporally coherent removal …
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 10.5
2026-08-11 · Guanlin Liu, Shaobin Ling, Renyuan Liu, Zeying Gong, Junjie Hu
Research Track A · General AI
Zero-shot object-goal navigation (ZSON) in open-vocabulary scenarios is challenging, as it requires a robot to locate an arbitrarily specified object in an unseen environment without task-specific training. Currently, the task still suffers from high latency and limited accuracy due to redundant perception pipelines an…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 9.8
2026-08-12 · Carlos Alberto Fernández-y-Fernández, Jorge R. Aguilar-Cisneros
General AI
The integration of large language models (LLMs) into software development workflows has given rise to a paradigm known as Agentic Software Engineering (SE 3.0), in which autonomous agents manage full development life cycles under human supervision. This paper presents an exploratory case study in which three LLM-based …
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 9.0
2026-08-12 · Beichen Huang, Zhenyu Liang, Bowen Zheng, Ran Cheng
General AI
Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persiste…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 8.8
2026-08-12 · Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini, Arman Khaledian
General AI
Large language models can extract richer signals from financial news than fixed sentiment lexicons, and recent work has explored feeding such signals into portfolio construction. We study an uncertainty-aware construction that feeds model-predicted risk -- decomposed into aleatoric and epistemic components -- directly …
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 8.8
2026-08-12 · Zhipeng Chang, Wenpeng Yin, Wenrui Hao
General AI
Many nonlinear models across physics, chemistry, and biology exhibit multiple solutions for the same parameters, and capturing this entire solution set is essential for understanding pattern-forming systems. Yet existing learned surrogates are fundamentally single-valued: neural operators map each parameter to a single…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 8.8
2026-08-12 · Rakib Ullah, Ruhul Islam Rahul, Tanbir Ahmed
General AI
Regional dialectal variation poses a fundamental challenge to natural language processing (NLP) in Bangla, where over 240 million speakers communicate across diverse regional variants that diverge significantly from Standard Colloquial Bangla (SCB) in phonology, morphology, and lexicon. Contemporary neural machine tran…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 8.8
2026-08-12 · Dongxu Tang, Shih Ying-Lei, Zhuoyi Ren, Jianting Liao, Yitian Shao
General AI
Understanding how lower-limb muscle groups coordinate is important for studying movement impairment, rehabilitation, and physical performance. Reproducible analysis of this coordination requires multimodal recordings that relate local muscle-related signals with body-level kinematics. Complementing neural-level electri…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 8.0
2026-08-11 · Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa, Jaehong Yoon, Xulei Yang, Nancy F. Chen, Xun Xu
General AI
Discrete diffusion models for categorical generation are defined by a corruption kernel, which determines the intermediate state space and the associated reverse prediction problem. We study uniform discrete diffusion and ask whether its training objective and reverse transitions can be enriched without changing the un…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 7.8
2026-08-12 · Samarth Sirsat, Anirudha Shinde, Amit Sethi, Aman Verma
General AI
Optimizing digital content headlines for click-through rate (CTR) is an important problem in online media and recommendation systems. While large language models (LLMs) have demonstrated strong generative capabilities, their effectiveness for discriminative ranking tasks, such as selecting the highest-performing headli…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 7.0
2026-08-11 · Albus W. Ng, Yi Han, Jusheng Zhang, Wenhao Wang
General AI
The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI. We argue this is structurally insufficient for autonomous agents that execute code, mutate files, send messages, and modify databases. Agent safety should be a runtime contract enforced by the…
- Review
- pending
- Role
- unreviewed
- Read
- later
huggingface
Score 6.0
2026-08-11 · Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae, Jihyong Oh
General AI
Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving strong generalization. However, enforcing explicit multi-view geometric consistency, e.g., through bundle adjustment, is computationally costly and is thus not imposed durin…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 5.8
2026-08-12 · AmirHossein Eshghi, Hamid Saadatfar, Seyyed Ali Hoseini, AmirMohsen Eshghi, Siavash Arjomand Bigdel
General AI
Class activation mapping (CAM) is one of the most widely used visual explanation families in explainable artificial intelligence. Its purpose is intuitive: it converts internal model evidence into a heatmap that highlights the image regions, convolutional channels, tokens, or patches that support a target class or conc…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 5.8
2026-08-12 · Anton V Ievlev, Heather Hare, Yiyang Li, Sergei V Kalinin
General AI
Time-of-flight secondary ion mass spectrometry (ToF-SIMS) is widely used for local chemical investigations across a broad range of materials and systems. However, its operation is expensive in expert time: a trained researcher must supervise acquisition throughout, dynamically tuning parameters throughout the experimen…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 5.8
2026-08-12 · Kenneth Desmond
General AI
We present \texttt{rcpgenerator}, an openly available code for generating $d$-dimensional dense, disordered, non-overlapping close packings from an arbitrary prescribed list of particle diameters. The method adapts the Clarke--Wiley inflation protocol, but instead uses the Adam optimizer to relax the particle configura…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 5.8
2026-08-12 · Yuyang Yin, Zixiang Li, Longxuan Deng, Hongkai Li, Shifang Zhao, Junnan Liu, Weirong Huang, Mengyu Wang, Tianxiao Fu, Yikai Wang, Peng-Shuai Wang, Xiaojie Jin, Yao Zhao, Yunchao Wei
General AI
Previsualization is an intermediate layer between ideas and production in film, games, architecture, and urban design. It lets creators iteratively refine scenes, actions, cameras, and spatial-temporal dynamics. Yet existing generative methods rely on simple prompts to jointly control all of these factors through one-s…
- Review
- pending
- Role
- unreviewed
- Read
- later