The paper introduces Interdomain Attention (IA), a hybrid architecture that blends softmax attention with recurrent memory within a single layer, leveraging a kernel regression perspective to compress keys and values into a state‑space model (SSM) memory. IA reconstructs the attention matrix implicitly from memory states, preserving the computational efficiency of SSMs while achieving performance gains. Experiments on models ranging from 125 M to 1.3 B parameters show IA surpasses an S4D baseline at matched memory size, outperforms standard Transformers on perplexity and common‑sense reasoning, and matches or exceeds SSM‑based models on genomic downstream tasks.
By Naoki Kiyohara, Harrison Bo Hua Zhu, Riccardo El Hassanin, Zhuo Sun, Wenlong Chen, Samir Bhatt, Yingzhen Li
arXiv:2610.27012v1 Announce Type: cross
Abstract: Reinforcement learning with verifiable rewards (RLVR) trains a language model by sampling responses, scoring them with an automatic verifier, and upd...
By Yunan Zeng, Jinhao Jing, Xi Cheng, Yuwang Wang
LightCRS is a lightweight, query‑conditioned framework that enables unified multi‑domain multimodal conversational recommendation by precomputing multimodal product representations with frozen encoders and fusing them online via a compact 5.3M‑parameter module using cross‑attention. The system shares parameters across all domains and employs an inter‑candidate Transformer to compare candidates jointly. On the newly constructed MM‑R2A‑25 benchmark, LightCRS achieves state‑of‑the‑art performance, improving HR@1 by 35.4% over the strongest baseline and reducing per‑query latency by 266×, while joint multi‑domain training alone boosts HR@1 by 15.2% compared to single‑domain models.
By He Ma, Lan You, Qiyang Wu, Chen Liu
The paper introduces RiseHarness, a framework that iteratively refines agent harnesses while keeping model weights fixed. It uses successful and failed runs under the same configuration to analyze failures, combining agent trajectories with runtime monitor traces to understand interactions between model actions and execution components. The framework then searches other harness frameworks for relevant implementations, adapts them, and validates changes through behavioral checks and repeated task evaluation, ultimately integrating mechanisms from multiple frameworks to improve reliability across tasks.
By Ruhan Wang, Yucheng Shi, Zongxia Li, Junyao Yang, Zhongzhi Li, Yue Yu, Haitao Mi, Dongruo Zhou, Leoweiliang
arXiv:2610.27626v1 Announce Type: new
Abstract: Multimodal Large Language Models show strong vision-language capabilities, yet their geometry-centric reasoning remains insufficiently understood. Exis...
By Jing Wang, Yitong Yang, Hao Dou, Yaomin Wu, Shuting He, Tingfei Shen, Jia Wu, Jiaqi Li, Yinglin Wang
arXiv:2610.27645v1 Announce Type: new
Abstract: As computer-use agents (CUAs) move to long-horizon workflows spanning multiple applications, undetected errors can silently corrupt persistent state an...
By Xu Hu, Haoming Li, Yuxiang Wang, Jinxin Yang, Kangshuo Li, Licheng Wang, Dingyi Kang, Jiayu Song, Tianhao Wang, Zhanhua Hu, Xu Yang, Qiannan Li, Bingzhe Li, Feng Chen
arXiv:2610.27699v1 Announce Type: new
Abstract: Low-bit quantization reduces the memory footprint of large language models, but preserving accuracy with efficient training remains challenging. Scalar...
By Xinyu Lei, Hong Huang, Jiebin Zhang, Hongyu Li, Jinlong Song, Decheng Wu, Guanghua Yu, Jianchen Zhu, Sujian Li
arXiv:2610.27777v1 Announce Type: new
Abstract: Tool-using LLM agents increasingly answer e-commerce queries through multi-step tool interactions. The expected output of a tool call can shift between...
By Wenshuo Zhang, Yuquan Lin, Yushi Sun, Yishi Lin, Rui Sheng, Peng He, Han Gao, Wang Jikai, Yifeng Rong
arXiv:2610.27817v1 Announce Type: new
Abstract: Every prompt sent to a hosted language model is readable by whoever runs it. We study whether the prompt can remain on the client while the host receiv...
By Mahendra Roopa, Srikanth Roopa
COMPASS is an agentic router that uses a capability-oriented model profiling approach to select large language models (LLMs) efficiently. It follows a routing recipe, gathers performance and cost evidence through tools, and can inspect candidate answers before making a selection. In evaluations on LLMRouterBench and DeepSWE, COMPASS improves accuracy while reducing model‑call cost compared to specialized and trained routing baselines, and it can adapt to new models without retraining.
By Amin Rezaei, Pouya Parsa
arXiv:2610.28121v1 Announce Type: new
Abstract: Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challe...
By Christopher Conrad, Deepak Panda, Weisi Guo, Antonios Tsourdos
arXiv:2610.28361v1 Announce Type: new
Abstract: Long-horizon deep search requires LLM agents to iteratively decompose complex information needs, gather evidence from external sources, and maintain a...
By Zijun Dou, Kun Luo, Chaofan Li, Shuqi Lu, Zheng Liu
arXiv:2610.28560v1 Announce Type: new
Abstract: Visual anomaly detection aims to detect abnormal objects, while anomaly samples are often scarce during model training. Assembling multiple pretrained...
By Shangquan Sun, Wenjun Luo, Xu He, Yoonsoo Lee, Shijian Lu
arXiv:2610.28595v1 Announce Type: new
Abstract: RTL repair benchmarks should measure whether a model can fix broken RTL given a specification. To this end, we construct and hash-bind RTLRepairDataset...
By Yeyin Eva Zhu, Rishabh Ranawat
arXiv:2606.23571v2 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly being integrated into first-principles computational workflows, yet their ability to configure scientif...
By Bin Shao, Jixiang Li, Xinyue Zhang, Baishun Yang, Zhiyang Liu, Weichao Wang
MOSS (Model Sanity Service) is a production framework that embeds LLM-based relevance scoring into a continuous monitoring loop for recommendation, search, and offer surfaces, using targeted sampling, strategy-aware prompting, and structured alerting to diagnose semantic failures. It has been deployed for over six months at a large U.S. retailer, identifying two confirmed serving defects and quantifying a 76.4% reduction in alert rate for a backfill blending fix. Benchmark results show that LLM judges outperform non-LLM baselines on both recommendation and search tasks, demonstrating that a single LLM monitoring framework can deliver actionable quality signals across multiple product discovery surfaces.
By Alina Nesen, Prathyusha Kanmanth Reddy, David Relyea, Rohit Avinash Mujumdar, Samaneh Karimi, Bo Shen, Jordan Hashemi
arXiv:2610.26938v1 Announce Type: cross
Abstract: Retrieval-Augmented Generation (RAG) is increasingly served across geo-distributed cloud and edge infrastructures, where wide-area latency, cross-reg...
By Hardik Ruparel, Raj Kumar Pandey, Pramod Kumar
arXiv:2610.26963v1 Announce Type: cross
Abstract: Discovering governing partial differential equations (PDEs) from observed data is a central inverse problem in computational science and engineering:...
By Langchen Liu, Junlin Luo, Min Zhu, Zhuoran Yang, Lu Lu
arXiv:2610.27233v1 Announce Type: cross
Abstract: Medical workflows often require multiple interdependent analyses, but existing specialist and generalist AI models are not designed to coordinate the...
By Ruoxin Wang, Yuanting Pan, Binxu Li, Ruiyang Ji, Yaqian Chen, Jiayuan Ding, Qifan Wang, Lifu Huang, Mingjie Li, Yu Zhang, Ehsan Adeli, Kilian Pohl, Zhe Xu, Zihao Lin, Haoyu Dong, Yixin Wang
arXiv:2610.27360v1 Announce Type: cross
Abstract: Scaling laws suggest that increasing model size, training data, and compute generally yields monotonic performance improvements. While this often hol...
By Rohit Saxena, Alessandro Suglia, Marek Rei, Pasquale Minervini