Knowledge catalogue
arXiv:2608.21097v1 Announce Type: new Abstract: LLM-as-Judge systems can produce multi-dimensional evaluations, such as trustworthiness, reliability, and factuality, and these outputs are often interp
I'm running Qwen 3.8 27B locally on a single GPU. I can push the context to 131k, but I'd rather run it faster at 64k if the agent can manage context properly. What I have in mind is pretty simple: on
Hi everyone, I'm currently working on optimizing an LLM setup at my company and I'm trying to identify where the actual performance bottleneck is. Our current setup is roughly: LLM: NVIDIA Nemotron mo
Gemax 1.9.15 — What’s new LAN server — share Gemax on your local network; open the real IP from another PC or phone Mobile-friendly UI — responsive layout for phone browsers on the same Wi‑Fi Workspac
arXiv:2608.19199v1 Announce Type: cross Abstract: We describe the evolution of a virtual assistant, called ATHENA, designed to support the capture, retrieval, and dissemination of knowledge for member
Hello gang, I made an implementation of DSpark PC Tree (Parent conditioned drafting tree). This is an implementation of this research paper: https://arxiv.org/abs/2608.02123 Unaffiliated, just found i
arXiv:2608.19218v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems are increasingly being explored for domain-specific maintenance and prognostics tasks, raising the
arXiv:2608.19231v1 Announce Type: cross Abstract: Estimating large and simulation-intensive discrete choice models (DCMs) requires repeated evaluation of utilities, probabilities, derivatives, and sim
It’s never been easier to start an AI-powered startup on Google Cloud. You grab an API key from Google AI Studio at breakfast, paste it into Antigravity, and by lunch you’ll have a nascent prototype o
arXiv:2608.18740v1 Announce Type: new Abstract: This paper proposes a multi-agent framework built on CrewAI [1] for conversational business intelligence. Five specialized AI agents operate in a sequen
Four days ago I released a hyper-optimized Qwen3.8-27B inference engine for an RTX 3090 (82 tps single request, 672 peak). Since then it went to ~114, then ~138 tps single-user with DFlash2 drafting a
arXiv:2608.18360v1 Announce Type: cross Abstract: Agentic AI systems take consequential actions governed by more than one pre-action control at once: authority, resource, and evidence gates that can a
arXiv:2608.18438v1 Announce Type: cross Abstract: Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a 'supervision gap' where novice therapists manage high
arXiv:2508.15436v2 Announce Type: replace-cross Abstract: We propose a extbf{P}latform for extbf{L}ayout-extbf{A}ware extbf{S}earch and extbf{M}emory extbf{A}rrangement (extbf{PLASMA}), a unified eval
arXiv:2608.18952v1 Announce Type: cross Abstract: Large language models can improve recommendation quality by reasoning explicitly over user history and candidate items - for example, extracting a use
arXiv:2608.18303v1 Announce Type: new Abstract: LLM-as-judge evaluation reduces response quality assessment to a single holistic A/B preference choice, providing no mechanism to isolate which quality
arXiv:2608.18105v1 Announce Type: cross Abstract: StocksTalk is a voice-enabled conversational system for transforming spoken financial screening requests into executable and validated structured quer
arXiv:2608.17148v1 Announce Type: cross Abstract: A personal language agent learns a fact from one audience and may later place it in the prompt it assembles for another. This memory-to-context step i
arXiv:2608.17756v1 Announce Type: new Abstract: Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization. Yet its multi
arXiv:2608.18034v1 Announce Type: new Abstract: Academic surveys play a central role in organizing rapidly expanding scholarly literature, yet their construction requires extensive paper analysis, coh
arXiv:2608.17950v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long contexts, yet the internal mechanisms enabling these dist
arXiv:2608.17694v1 Announce Type: cross Abstract: Existing LLM-based approaches to Architecture Decision Record (ADR) generation share a critical and largely unexamined assumption: that input is alrea
arXiv:2602.14784v1 Announce Type: cross Abstract: Breaking long documents into smaller segments is a fundamental challenge in information retrieval. Whether for search engines, question-answering syst
arXiv:2509.10818v2 Announce Type: replace Abstract: When consequential decisions depend on knowledge that exists nowhere in writing, LLMs hallucinate not from retrieval failure but from model absence.
arXiv:2608.16921v2 Announce Type: cross Abstract: Effective cybersecurity operations require timely and accurate analysis of large-scale heterogeneous security information; however, analysts increasin
arXiv:2608.17781v1 Announce Type: new Abstract: ML systems increasingly condition decisions on downstream model identity, but this is useful only if model-specific differences form reusable structure
Rob Strechay, until recently managing director and principal analyst at theCUBE Research, has joined VentureBeat as our first Lead Analyst and a founding analyst of VentureBeat Research. His arrival i
arXiv:2608.16924v1 Announce Type: cross Abstract: This work-in-progress (WIP) innovative practice category paper presents LLM Odyssey, an open source, browser-based serious gaming platform comprising
arXiv:2602.22456v2 Announce Type: replace-cross Abstract: Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpi
arXiv:2608.15082v1 Announce Type: new Abstract: Cold chain logistics has advanced technologically, yet most deployed systems remain reactive monitors, not decision-making agents: thresholds trigger al
arXiv:2505.02763v2 Announce Type: replace-cross Abstract: One of the central promises of legal AI is to automate drudgery -- the formal, repetitive tasks of lawyers' work that consume time without cal
arXiv:2608.16508v1 Announce Type: cross Abstract: We propose a two-stage large language model (LLM) framework for zero-shot detection of insider threats and advanced persistent threats (APTs) from het
arXiv:2608.15211v1 Announce Type: new Abstract: Training high-resolution AI-based Earth forecasting models is memory-intensive. Window-based Swin Transformers reduce the quadratic cost of global atten
arXiv:2608.16096v1 Announce Type: cross Abstract: Enterprises connect language models to their own data through retrieval. The benchmarks that rank multi-hop retrieval systems leave out two facts a bu
arXiv:2608.14588v1 Announce Type: new Abstract: Sequential multi-agent LLM pipelines chain specialized agents without verification at handoffs, creating a structural flaw with measurable and severe co
arXiv:2608.13626v1 Announce Type: new Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map. We test whether action maps fitted without a source
arXiv:2608.14320v1 Announce Type: new Abstract: The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment toward itself. This effect is well established in h
arXiv:2608.13730v1 Announce Type: cross Abstract: Empirical reports on the true cost of AI-intensive software development remain scarce, and the few that exist are easy to get wrong in ways that never
arXiv:2608.13883v1 Announce Type: new Abstract: Most agent-memory benchmarks test post-hoc recall, whereas MemoryArena evaluates whether memory supports interdependent, multi-session task completion.
Yes, it sucks to waste time waiting on 16K+ reasoning tokens alone. But here's the thing, this is only a 27B model trying to perform on par with 1T+ parameter models. Something has to be sacrificed, a
arXiv:2608.13959v1 Announce Type: new Abstract: Function calling is what the recent accounting of constrained generation explicitly sets aside: it finds the decoder's contribution small for format con
arXiv:2608.13472v1 Announce Type: cross Abstract: Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition.
Most Ollama frontends I've tried are chat UIs with tool calling bolted on as an afterthought, which is fine until you actually try to make a small local model do multi-step work and it silently emits
arXiv:2603.14501v2 Announce Type: replace-cross Abstract: Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resou
arXiv:2608.12987v1 Announce Type: cross Abstract: Generative information retrieval (GIR) has emerged as a compelling alternative to the conventional index-retrieve-then-rank retrieval pipeline by trai
arXiv:2608.12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals. In these settings, fin
arXiv:2608.12984v1 Announce Type: cross Abstract: Long-form research reports generated by large language models drift, contradict themselves, and lose provenance: the same metric appears with differen
arXiv:2608.12529v1 Announce Type: cross Abstract: Motivation: LinkML is a suitable language for the representation of the structural and content constraints of different kinds of biomedical data. Even
The maximum frame count allowed by the native 'MiniMax H3 Reference to Video' node technically is 1008, even if that's way over the training range of the model, which is 324 frames. But why not try? S
arXiv:2603.24060v3 Announce Type: replace Abstract: Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environm
arXiv:2608.10480v1 Announce Type: new Abstract: Large language models (LLMs) are widely applied across chemical tasks, such as molecular property prediction, which underpins drug discovery. Molecular
arXiv:2608.10385v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assess
arXiv:2608.10963v1 Announce Type: new Abstract: We present the REAP system for the AKBC Shared Task 2026 on constructing knowledge bases from language models in a closed-book setting, subject to a bud
arXiv:2608.10224v1 Announce Type: new Abstract: Enterprise support agents operate in rapidly changing environments where policies, product capabilities, and knowledge bases evolve continuously, making
When should you start post-training your own models? @FireworksAI_HQ CEO @lqiao’s answer: after product-market fit. Not because it's hard... but because only after PMF is the data coming off your prod
arXiv:2608.09142v1 Announce Type: new Abstract: Treatment planning in precision oncology requires synthesizing heterogeneous patient information with rapidly evolving clinical guidelines to ensure gui
arXiv:2608.08732v1 Announce Type: cross Abstract: Multi-vector vision-language retrievers enable fine-grained Visual Document Retrieval (VDR) through late interaction, but storing and scoring hundreds
Hi LocalLlama, we're super excited to release Unsloth Desktop today! 🦥 It's the first desktop app that enables you to run and train models locally. Open-source. Available on Mac, Windows, and Linux Su
arXiv:2608.09507v1 Announce Type: cross Abstract: Natural language user preferences provide an interpretable interface for LLM personalization. However, universal preference summaries often contain in
arXiv:2608.08211v1 Announce Type: cross Abstract: Recent low-light image enhancement (LLIE) methods have driven brightness and structural fidelity close to that of normally-exposed images, yet their o