arXiv:2607.20438v1 Announce Type: new Abstract: Preference-based post-training is usually understood through endpoint behavior, yet the learned update that produces this behavior remains largely opaque. We study…
arXiv:2607.21019v1 Announce Type: cross Abstract: Traditional approaches to wearable health signal analysis, such as smartwatches, are constrained by rigid analytical frameworks and limited personalisation. The emergence…
arXiv:2607.20437v1 Announce Type: new Abstract: Production Retrieval Augmented Generation (RAG) systems rely on aggregating multiple external documents to answer complex queries. However, the retrieved documents introduce…
arXiv:2607.20709v1 Announce Type: cross Abstract: Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agents (NOOA),…
arXiv:2607.20436v1 Announce Type: new Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption. A…
arXiv:2607.20491v1 Announce Type: cross Abstract: Standard evaluation benchmarks measure what a tool-using agent decides, not whether it arrives at that decision through the same process each…
arXiv:2607.20435v1 Announce Type: new Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly…
arXiv:2607.21574v1 Announce Type: new Abstract: Surprisal theory holds that the human processing difficulty of a linguistic unit in context is an affine function of its surprisal…
arXiv:2607.20434v1 Announce Type: new Abstract: As the parameter size of language models continues to grow, effective model compression is required to reduce their computational and memory…
arXiv:2607.20433v1 Announce Type: new Abstract: While language models remain frozen at their training state, the world evolves continuously. Knowledge editing has emerged as a key alternative…
arXiv:2605.28346v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly evaluated for whether they identify the right visual content, but little is known about whether they…
arXiv:2607.20427v1 Announce Type: new Abstract: Mixture-of-Experts architectures have revolutionized scaling, yet the underlying logic of their routing remains a black box. In this paper, we uncover…
arXiv:2607.20428v1 Announce Type: new Abstract: This study evaluated a retrieval-augmented, multi-agent large language model (LLM)-driven, human-in-the-loop framework for detecting cutaneous immune-related adverse events (cirAEs) from clinical…
arXiv:2607.20429v1 Announce Type: new Abstract: Large language models are increasingly used to simulate diverse human opinions in open-ended tasks such as synthetic surveys, focus group modeling,…
arXiv:2607.20431v1 Announce Type: new Abstract: Materials science literature analysis requires simultaneous attention to composition, processing, characterization, and property relationships, yet conventional retrieval-augmented generation pipelines struggle to…
arXiv:2607.20430v1 Announce Type: new Abstract: We present LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining in UN and…
arXiv:2602.13792v3 Announce Type: replace-cross Abstract: Artificial intelligence built on large foundation models has transformed language understanding, computer vision, and reasoning, yet these systems remain isolated and…
arXiv:2607.20432v1 Announce Type: new Abstract: Recent advances in large language models and their widespread adoption have prompted claims that natural language could entirely replace formal languages,…
arXiv:2607.20553v1 Announce Type: cross Abstract: Memory Manager models are pivotal in agent systems. Existing methods rely predominantly on LLM-judged synthetic question-answer (QA) pairs, making memory valuation…
arXiv:2607.20479v1 Announce Type: cross Abstract: Training probes to detect deceptive outputs from large language models is still an open problem. Recent work has demonstrated that detection…
arXiv:2607.21412v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially in safety-critical…
arXiv:2607.20864v1 Announce Type: cross Abstract: Position bias in multiple-choice LLM evaluation is widely cited as a confound in capability comparisons, but published measurements rely on single…
arXiv:2604.01925v2 Announce Type: replace Abstract: Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity…
arXiv:2509.14257v3 Announce Type: replace Abstract: Large Language Model agents achieve strong performance on multi-step reasoning and tool-use tasks, but their impressive capabilities typically rely on extremely…