Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2601.14286v2 Announce Type: replace-cross Abstract: Traditional technology mapping suffers from systemic inaccuracies in delay estimation due to its reliance on abstract, technology-agnostic de...
arXiv:2604.02103v3 Announce Type: replace-cross Abstract: Realistic online handwriting depends not only on individual character shapes, but also on how a writer connects, spaces, and aligns adjacent...
arXiv:2605.10681v2 Announce Type: replace-cross Abstract: Forward error correction is essential for reliable communication over noisy channels. Attention-based model-free neural decoders have shown s...
arXiv:2605.27690v2 Announce Type: replace-cross Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate st...
arXiv:2608.29601v2 Announce Type: replace-cross Abstract: We present $N_0$-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale mul...
arXiv:2609.22090v1 Announce Type: new Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Ps...
arXiv:2609.22111v1 Announce Type: new Abstract: Large language model agents are increasingly capable of conducting research autonomously, producing research documents alongside the code and experimen...
arXiv:2609.22114v1 Announce Type: new Abstract: Context compression is widely proposed as a way to cut the token bill of LLM coding agents, and public benchmarks report that aggressive compression pr...
arXiv:2609.22200v1 Announce Type: new Abstract: LLM assistants and agentic systems log long multi-turn conversations. AI providers often scan these conversations for Personally Identifiable Informati...
arXiv:2609.22235v1 Announce Type: new Abstract: While multi-agent systems based on large language models (LLMs) have shown promise in automating the progressive workflow of academic research, extendi...
arXiv:2609.22255v1 Announce Type: new Abstract: Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent...
arXiv:2609.22259v1 Announce Type: new Abstract: Context layers, curated documentation that an analytics agent fetches at query time, produce large accuracy gains on text-to-SQL benchmarks. A with/wit...
arXiv:2609.22409v1 Announce Type: new Abstract: Understanding contextual causality is critical for large language models (LLMs), as it enables them to accurately identify causal relations in specific...
arXiv:2609.22778v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used as evaluators, yet their reliability in professional assessment tasks that require exper...
arXiv:2609.23088v1 Announce Type: new Abstract: Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, and provide appropriate instructiona...
arXiv:2609.23191v1 Announce Type: new Abstract: Speech-text space alignment is a multimodal representation learning method consisting to map different speech and text into a shared representation spa...
arXiv:2609.23231v1 Announce Type: new Abstract: Cross-lingual information retrieval (CLIR) is increasingly important in multi-national industries, where critical technical evidence may exist in a dif...
arXiv:2609.23490v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly execute multi-step workflows through tool use and interaction with users and environments. However, curr...
arXiv:2609.23267v1 Announce Type: new Abstract: The visual modality, i.e., images, plays a key role in multi-modal entity alignment (MMEA). Existing approaches often directly fuse the image with othe...
arXiv:2609.23726v1 Announce Type: new Abstract: Large language models have shown strong performance across a range of legal tasks, but existing benchmarks rarely evaluate the ability to take and defe...