Papers
Research papers from arXiv and related sources
CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code l...
Lintang Sutawika, Aditya Bharat Soni, Bharath Sriraam R R, Apurva Gandhi, Taha Yassine, Sanidhya ...
FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair
Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifacts such as GUI sc...
Ruize Ma, Yilei Jiang, Shilin Zhang, Zheng Ma, Yi Feng, Vincent Ng, Zhi Wang, Xiangyu Yue, Chuany...
Discovering Decoupled Functional Modules in Large Language Models
Understanding the internal functional organization of Large Language Models (LLMs) is crucial for improving their trustworthiness and performance. However, how LLMs organize different functions int...
Yanke Yu, Jin Li, Ying Sun, Ping Li, Zhefeng Wang, Yi Zheng
CodeT5-RNN: Reinforcing Contextual Embeddings for Enhanced Code Comprehension
Contextual embeddings generated by LLMs exhibit strong positional inductive biases, which can limit their ability to fully capture long-range, order-sensitive dependencies in highly structured sour...
Md Mostafizer Rahman, Ariful Islam Shiplu, Yutaka Watanobe, Md Faizul Ibne Amin, Syed Rameez Naqv...
Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gain
Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by...
Corentin Royer, Debarun Bhattacharjya, Gaetano Rossiello, Andrea Giovannini, Mennatallah El-Assady
Swarm: Co-Activation Aware KVCache Offloading Across Multiple SSDs
The key-value (KV) cache has become the dominant contributor to memory consumption in large language model (LLM) inference. Although offloading KVCache from GPU high-bandwidth memory (HBM) to CPU D...
Tuowei Wang, Liyun Chu, Ruwen Fan, Ju Ren
Governed Memory: A Production Architecture for Multi-Agent Workflows
Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges aris...
Hamed Taheri
Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory
Large language models increasingly serve as persistent knowledge workers, with in-context memory - facts stored in the prompt - as the default strategy. We benchmark in-context memory against Knowl...
Oliver Zahn, Simran Chana
Large Language Models in Teaching and Learning: Reflections on Implementing an AI Chatbot in Higher Education
The landscape of education is changing rapidly, shaped by emerging pedagogical approaches, technological innovations such as artificial intelligence (AI), and evolving societal expectations, all of...
Fiammetta Caccavale, Carina L. Gargalo, Julian Kager, Magdalena Skowyra, Steen Larsen, Krist V. G...
Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation
Universal medical image segmentation seeks to use a single foundational model to handle diverse tasks across multiple imaging modalities. However, existing approaches often rely heavily on manual v...
Haoyun Chen, Fenghe Tang, Wenxin Ma, Shaohua Kevin Zhou
Fast stabilizer state preparation via AI-optimized graph decimation
We propose a general method for preparing stabilizer states with reduced two-qubit gate count and depth compared to the state of the art. The method starts from a graph state representation of the ...
Michael Doherty, Matteo Puviani, Jasmine Brewer, Gabriel Matos, David Amaro, Ben Criger, David T....
Embedding World Knowledge into Tabular Models: Towards Best Practices for Embedding Pipeline Design
Embeddings are a powerful way to enrich data-driven machine learning models with the world knowledge of large language models (LLMs). Yet, there is limited evidence on how to design effective LLM-b...
Oksana Kolomenko, Ricardo Knauer, Erik Rodner
LR-Robot: A Unified Supervised Intelligent Framework for Real-Time Systematic Literature Reviews with Large Language Models
Recent advances in artificial intelligence (AI) and natural language processing (NLP) have enabled tools to support systematic literature reviews (SLRs), yet existing frameworks often produce outpu...
Wei Wei, Jin Zheng, Zining Wang
DiffVP: Differential Visual Semantic Prompting for LLM-Based CT Report Generation
While large language models (LLMs) have advanced CT report generation, existing methods typically encode 3D volumes holistically, failing to distinguish informative cues from redundant anatomical b...
Yuhe Tian, Kun Zhang, Haoran Ma, Rui Yan, Yingtai Li, Rongsheng Wang, Shaohua Kevin Zhou
Machine Learning for Network Attacks Classification and Statistical Evaluation of Machine Learning for Network Attacks Classification and Adversarial Learning Methodologies for Synthetic Data Generation
Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more s...
Iakovos-Christos Zarkadis, Christos Douligeris
Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3)
Previous work has reported that vision foundation models show promising zero-shot performance in eye image segmentation. Here we examine whether the latest iteration of the Segment Anything Model, ...
Diederick C. Niehorster, Marcus Nyström
Electron-Hole Scattering Dichotomy and Anisotropic Warping in Quasi-Two-Dimensional Fermi Surfaces of UTe2
We present a combined experimental and theoretical study of the detailed Fermi-surface (FS) geometry of UTe2, a heavy-fermion superconductor that has recently attracted considerable attention as a ...
Motoi Kimata, Jun Ishizuka, Freya Husstedt, Yusei Shimizu, Ai Nakamura, Dexin Li, Yoshiya Homma, ...
Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation
Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data. Although pretrained Vision Foundation Models (VFMs) ...
Haocheng Li, Juepeng Zheng, Shuangxi Miao, Ruibo Lu, Guosheng Cai, Haohuan Fu, Jianxi Huang
MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment
In the real economy, modern decision-making is fundamentally challenged by high-dimensional, multimodal environments, which are further complicated by agent heterogeneity and combinatorial data spa...
Yusen Wu, Yiran Liu, Xiaotie Deng
Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization
For LLM trading agents to be genuinely trustworthy, they must demonstrate understanding of market dynamics rather than exploitation of memorized ticker associations. Building responsible multi-agen...
Joohyoung Jeon, Hongchul Lee