Knowledge catalogue
arXiv:2608.17336v1 Announce Type: new Abstract: Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic q
arXiv:2608.17719v1 Announce Type: cross Abstract: Context: Software systems that depend on commercial large language model APIs must migrate to successor versions when vendors deprecate older models.
DeepSeek released on a paper on pretrained engrams in January. I’m surprised ds didn’t release engrams with v4 pro. When will ds or another lab release a fixed engram model? Fixed engrams will be the
arXiv:2608.15565v1 Announce Type: new Abstract: Experience-learning agents for optimization modeling improve by storing verified skills, but existing learners admit knowledge by checking against known
arXiv:2608.15108v1 Announce Type: cross Abstract: Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identitie
arXiv:2608.14813v1 Announce Type: new Abstract: Despite a strong interest on the part of the research community in the topic of trustworthy and safe AI, the composition of the text corpora that large
arXiv:2608.15772v1 Announce Type: new Abstract: When a language model refuses to answer a prompt, it is unclear whether the correct answer is erased from its internal representations, or merely suppre
arXiv:2608.16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks. Such deployments impose
arXiv:2608.14737v1 Announce Type: cross Abstract: This study analyses LLMs in imbalanced binary classification, using study screening in systematic reviews as the application domain. An experiment was
arXiv:2608.16246v1 Announce Type: cross Abstract: Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for
arXiv:2608.15109v1 Announce Type: new Abstract: Generating structurally valid synthetic tabular data remains difficult: outputs with high statistical fidelity and downstream utility can still violate
arXiv:2608.15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlo
arXiv:2604.03904v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often produce confident but incorrect answers, in part because standard evaluation incentives reward guessing ove
arXiv:2608.16739v1 Announce Type: new Abstract: Reinforcement learning algorithms for Large Language Models (LLMs) are largely distinguished by their variance reduction strategy. Group-relative method
arXiv:2608.15451v1 Announce Type: new Abstract: Large language models process large amounts of information but usually lack an explicit mechanism for maintaining compact and evolving conceptual repres
arXiv:2608.16181v1 Announce Type: cross Abstract: Recent advances in large language models have enabled a new class of agentic data science systems that allow users to complete complex data science wo
arXiv:2608.15436v1 Announce Type: new Abstract: Frontier AI models have advanced rapidly, but they still struggle with telecom-specific tasks. We present Open Telco (OTel), an open telecom AI resource
arXiv:2608.16650v1 Announce Type: new Abstract: Large language models (LLMs) exhibit sycophancy, a tendency to agree with user beliefs regardless of factual accuracy. This can reinforce misconceptions
arXiv:2608.16419v1 Announce Type: cross Abstract: Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here
arXiv:2608.16003v1 Announce Type: new Abstract: Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer. We ask whether that wiring
arXiv:2608.15567v1 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) enables the deployment of large language models under tight memory budgets, but accuracy often collapses at
arXiv:2608.16553v1 Announce Type: new Abstract: Multi-preference alignment is often framed as scalarization: combine reward dimensions, then optimize. This leaves a temporal decision underspecified: w
arXiv:2608.15665v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables backpropagation-free fine-tuning of large language models, but existing ZO methods suffer from high-variance grad
arXiv:2607.14345v4 Announce Type: replace-cross Abstract: People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: th
arXiv:2608.16391v1 Announce Type: cross Abstract: As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the eco
arXiv:2608.15092v1 Announce Type: cross Abstract: In this work, we introduce WeSCE, a benchmark for quantifying security drift in code editing under weak-security constraints, where tasks specify only
If you're running Ollama, llama.cpp, or vLLM behind nginx or HAProxy for more than a single user, you've probably hit this: nginx treats a 10-token prompt and a 10k-token prompt as identical 'one requ
arXiv:2608.13944v1 Announce Type: cross Abstract: This paper examines a use of AI in creative practice as an interpretive sounding board for human-generated material, rather than the more familiar pat
arXiv:2608.13607v1 Announce Type: new Abstract: Frontier LLMs are updated frequently and typically outperform their predecessors in aggregate. But aggregate gains say little about individual samples:
arXiv:2608.13612v1 Announce Type: new Abstract: Natural-language interfaces to enterprise data must translate underspecified requests into governed, executable behavior while controlling invalid queri
arXiv:2608.12679v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in discovery domains such as math and science. The usual approach is to present the problem to th
arXiv:2608.12350v1 Announce Type: cross Abstract: The energy demand growth and environmental impacts of artificial intelligence (AI) have generated substantial interest in supplying sufficient low-cos
arXiv:2608.13426v1 Announce Type: cross Abstract: Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplicati
arXiv:2608.13173v1 Announce Type: new Abstract: Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Exist
arXiv:2608.13179v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its tra
arXiv:2512.06547v4 Announce Type: replace-cross Abstract: Decoupled PPO has been a successful reinforcement learning (RL) algorithm to deal with the high data staleness under the asynchronous RL setti
arXiv:2604.14401v2 Announce Type: replace Abstract: Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-making in continuously evolving conditions. As suc
arXiv:2608.11226v1 Announce Type: new Abstract: Reinforcement-learning post-training dominates modern language-model development, yet its power behavior on GPU hardware has not been characterized, and
There's no training anywhere in this. I ported Doom's actual rendering algorithm into transformer weights using a compiler I wrote (torchwright) -- every weight computed, none learned. The prompt carr
arXiv:2608.11584v1 Announce Type: new Abstract: Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.8% of responses meet all requireme
arXiv:2608.11493v1 Announce Type: new Abstract: Traditional offline recommendation evaluation relies heavily on complex, manually maintained feature pipelines that are difficult to scale. While Large
arXiv:2608.12097v1 Announce Type: new Abstract: Rubric-based evaluators commonly treat rubrics as prompt context or flat criteria: they specify what to judge but leave criterion composition implicit,
arXiv:2608.11408v1 Announce Type: new Abstract: Prior white-box studies show that large language models can retain latent traces of target knowledge after unlearning, even when the knowledge is no lon
arXiv:2608.11694v1 Announce Type: cross Abstract: A benchmark score comes from a single phrasing of each problem. That single phrasing is treated as if it stood for the whole space of ways the same pr
arXiv:2608.12150v1 Announce Type: new Abstract: Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the toke
arXiv:2608.10545v1 Announce Type: cross Abstract: Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node. Ho
arXiv:2608.10315v1 Announce Type: cross Abstract: Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or s
arXiv:2608.10725v1 Announce Type: new Abstract: Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models
arXiv:2608.10447v1 Announce Type: cross Abstract: Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predi
arXiv:2608.11047v1 Announce Type: new Abstract: While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains compar
arXiv:2504.18587v2 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful approach for improving the reasoning capabilities of large language models, as demonstrated b
arXiv:2608.09217v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform tas
arXiv:2608.08160v1 Announce Type: cross Abstract: The rapid advancement of Large Language Models (LLMs) is revolutionizing AI for Games by enabling open-ended and fluid interactive storytelling. Howev
arXiv:2608.09485v1 Announce Type: new Abstract: Cooperative capabilities in language models are dual-use. The same social reasoning that supports civic deliberation can also enable strategic omission,
arXiv:2608.07622v1 Announce Type: new Abstract: Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience. Yet memory e
arXiv:2608.09900v1 Announce Type: new Abstract: Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably wa
arXiv:2608.09187v1 Announce Type: new Abstract: A long-form translation request can succeed at the API layer and still produce an unusable result. The output may be empty, truncated, filtered, dominat
arXiv:2608.07523v1 Announce Type: cross Abstract: Difficulty differences across parallel-class programming examinations affect the fairness of course assessment. This study repositions large language
arXiv:2608.08722v1 Announce Type: cross Abstract: Benchmarks for systems that are optimized against the evaluation signal measure something different from what they claim. We document this concretely
arXiv:2608.08056v1 Announce Type: new Abstract: Medical data, by its nature, exhibit a high degree of heterogeneity on multiple levels ranging from (a) different modalities like images, text and time