Stay updated with the latest research and technology news
arXiv:2601.04765v3 Announce Type: replace Abstract: We study how syntactic and semantic information is encoded in inner layer representations of Large Language Models (LLMs), focusing on...
arXiv:2601.04861v2 Announce Type: replace Abstract: While multi-agent systems (MAS) have demonstrated superior performance over single-agent approaches in complex reasoning tasks, they often suffer from significant...
arXiv:2601.04886v2 Announce Type: replace Abstract: Pull request (PR) descriptions generated by AI coding agents are the primary channel for communicating code changes to human reviewers....
arXiv:2601.05171v2 Announce Type: replace Abstract: Existing long-term personalized dialogue systems struggle to reconcile unbounded interaction streams with finite context constraints, often succumbing to memory noise...
arXiv:2601.05208v3 Announce Type: replace Abstract: We propose a simple yet effective approach to enhance the performance of feed-forward 3D reconstruction models. Existing methods often struggle...
arXiv:2601.05225v2 Announce Type: replace Abstract: Augmentation makes search trees tremendously more versatile, allowing them to support efficient aggregation queries, order-statistic queries, and range queries in...
arXiv:2601.05344v3 Announce Type: replace Abstract: The ability to construct mental models of the world is a central aspect of understanding. Similarly, visual understanding can be...
arXiv:2601.05679v5 Announce Type: replace Abstract: We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give...
arXiv:2601.06117v2 Announce Type: replace Abstract: A central question in artificial intelligence is whether models learn universal laws or merely memorize statistical heuristics. This distinction is...
arXiv:2601.07110v2 Announce Type: replace Abstract: Synthetic personas are widely used to condition large language models (LLMs) for social simulation, yet most personas are still constructed...
arXiv:2601.07154v2 Announce Type: replace Abstract: From Vision-Language-Action (VLA) systems to robotics, existing egocentric datasets primarily focus on action recognition tasks, while largely overlooking the inherent...
arXiv:2601.07251v3 Announce Type: replace Abstract: Recent advancements have expanded the role of Large Language Models in board games from playing agents to creative co-designers. However,...
arXiv:2601.07974v2 Announce Type: replace Abstract: AI-text detectors achieve high accuracy on in-domain benchmarks, but often struggle to generalize across different generation conditions such as unseen...
arXiv:2601.08209v2 Announce Type: replace Abstract: In domains such as biomedicine, materials, and finance, high-stakes deployment of large language models (LLMs) requires injecting private, domain-specific knowledge...
arXiv:2601.08235v3 Announce Type: replace Abstract: As language-model agents evolve from passive chatbots into proactive assistants that handle personal data, evaluating their adherence to social norms...
arXiv:2601.08258v2 Announce Type: replace Abstract: We introduce T3 (Testing Trustworthy Thinking), a diagnostic benchmark designed to rigorously evaluate LLM causal judgment across Pearl's Ladder of...
arXiv:2601.08387v2 Announce Type: replace Abstract: In this paper, we present an efficient algorithm to sample random sparse matrices to be used as check matrices for...
arXiv:2601.08641v2 Announce Type: replace Abstract: Copy trading has become the dominant entry strategy in meme coin markets. However, due to the market's extreme illiquid and...
arXiv:2601.08653v2 Announce Type: replace Abstract: Large Language Models are rapidly emerging as web-native interfaces to social platforms. On the social web, users frequently have ambiguous...
arXiv:2601.08815v2 Announce Type: replace Abstract: The Contract Net Protocol (1980) introduced coordination through contracts in multi-agent systems. Modern agent protocols standardize connectivity and interoperability; yet,...
arXiv:2601.09026v2 Announce Type: replace Abstract: We present a new training methodology for transformers using a multilevel, layer-parallel approach. Through a neural ODE formulation of transformers,...
arXiv:2601.09028v2 Announce Type: replace Abstract: The development of large language models (LLMs) has achieved superior performance in a range of downstream tasks, including LLM-based retrieval-augmented...
arXiv:2601.09033v2 Announce Type: replace Abstract: Generative AI (GenAI) is increasingly used in academic writing, yet its effects on students' writing self-efficacy remain contingent on how...
arXiv:2601.09053v2 Announce Type: replace Abstract: In this study, we evaluate a locally-deployed large-language model (LLM) to convert unstructured endometriosis transvaginal ultrasound (eTVUS) scan reports into...