Running local LLM's as agents in Claude Code
I hit my token limit three times a day on my max subscription - got sick of that and designed this MCP setup to shift some of the coding load to my local Qwen3.8-27B model. I've been iterating on it n
Knowledge catalogue
I hit my token limit three times a day on my max subscription - got sick of that and designed this MCP setup to shift some of the coding load to my local Qwen3.8-27B model. I've been iterating on it n
arXiv:2608.25459v1 Announce Type: new Abstract: Industrial aerial robotics demands safety guarantees for navigation in unstructured environments while optimizing performance and computational efficien
arXiv:2608.25529v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding. However, their ability to follow instructions in this dom
arXiv:2608.24441v1 Announce Type: new Abstract: Electric vehicle (EV) charging loads exhibit strong behavioral heterogeneity and temporal variability, posing significant challenges for online probabil
arXiv:2510.21536v5 Announce Type: replace-cross Abstract: Free-space segmentation is essential for autonomous robots to identify drivable regions and navigate safely across indoor, outdoor, and road-s
arXiv:2608.23776v1 Announce Type: cross Abstract: Understanding human skill is important for AI systems that collaborate with, coach, or assist people. Unlike typical latent variable estimation proble
arXiv:2608.23863v1 Announce Type: new Abstract: Robots are beginning to act on world-model predictions, yet reliability is still expressed through instantaneous, model-internal signals. DreamLedger in
arXiv:2608.24524v1 Announce Type: cross Abstract: Feature attribution is a central tool of model interpretability, yet the software through which it is applied remains fragmented: individual tools spe
arXiv:2608.24804v1 Announce Type: new Abstract: We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed. The evolved harness can include
arXiv:2608.23601v1 Announce Type: cross Abstract: EDA flow parameter tuning is critical for quality-of-results~(QoR), yet the parameter space is large, tightly coupled, and full evaluations are prohib
arXiv:2608.21444v1 Announce Type: new Abstract: Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring. Yet
arXiv:2608.22421v1 Announce Type: new Abstract: World models predict action-conditioned futures and serve as critical internal simulators for downstream planning and control. However, catastrophic pre
arXiv:2608.20390v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) are increasingly used to answer religious questions, but for Islamic content they carry two serious risks
arXiv:2608.20886v1 Announce Type: new Abstract: Real-world image search queries are multimodal and compositional: ``find this shirt in pink'' specifies an entity to retain, an attribute to modify, and
arXiv:2608.20748v1 Announce Type: new Abstract: The Visual Geometry Grounded Transformer (VGGT) enables unified feed-forward 3D reconstruction from multi-view images. However, deploying such a high-pe
arXiv:2510.09930v2 Announce Type: replace-cross Abstract: Real-world systems, ranging from industrial manufacturing to wearable healthcare, generate multivariate time series with hierarchical states r
Thanks to Unsloth Dynamic 3.0 quants coming in slightly leaner and better preserved, I settled on Qwen 3.8 27B (`UD_Q4_K_XL`) at 100K context as my daily driver for Hermes Agent and OpenCode. On an RT
arXiv:2608.20965v1 Announce Type: new Abstract: We define an atomic generation fact f=(u,tau,omega,z;rho), recording the origin, realized transformation, concrete occurrence, generated result and rela
arXiv:2608.20338v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and bench
arXiv:2608.19491v1 Announce Type: cross Abstract: Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate. How
arXiv:2606.05605v2 Announce Type: replace Abstract: How does a system that merely predicts the world come to distinguish its own causal influence from everything else? We trace this transition in a mi
arXiv:2608.20201v1 Announce Type: new Abstract: Software form has undergone two paradigm shifts since its inception: Software 1.0, in which instructions determine behavior, and Software 2.0, in which
arXiv:2608.18306v1 Announce Type: new Abstract: Single-photon cameras based on single-photon avalanche diode (SPAD) technology are gaining popularity for 3D sensing, thanks to their extreme sensitivit
arXiv:2608.18597v1 Announce Type: new Abstract: Protein language models are widely used priors for protein sequence design, and a growing body of work controls them at inference time as an alternative
Hey everyone, Posted TinySearch here a few versions ago and got a bunch of useful feedback, so figured I'd post an update because the thing has changed quite a bit since then. Repo: [https://github.co
arXiv:2608.19125v1 Announce Type: new Abstract: When an expert corrects an LLM assistant's error, the correction usually dies with the session, and the error class returns. I argue this is an operatio
arXiv:2608.17843v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance on structured reasoning tasks, but what they encode and whether it informs model beh
arXiv:2608.18061v1 Announce Type: new Abstract: We give a two-player zero-sum repeated game between a learner and nature whose value identity generates Bayesian updating and an exact accounting of exp
arXiv:2510.08713v3 Announce Type: replace Abstract: Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typical
Zep offers a knowledge graph for persistent user memory and shared organisational context through MCP, according to Zep.
For financial institutions, operational resilience has long been embedded in regulatory and supervisory expectations — to say nothing of the high expectations of consumers. With the implementation of
arXiv:2608.15952v1 Announce Type: cross Abstract: Differences between high-energy event generators can arise at several stages of the collision simulation, from the hard scattering through parton show
arXiv:2608.15579v1 Announce Type: cross Abstract: Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long
arXiv:2608.16185v1 Announce Type: cross Abstract: LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (sp
arXiv:2608.14717v1 Announce Type: new Abstract: A query-relation deletion can improve the edited slot while reducing the utility of the prediction set that contains it. We study this tension in two re
I gave three AI models the same brief: build a premium Three.js fragrance launch site from the same Git baseline, independently and with no collaboration. Three very different results. Here’s the full
arXiv:2608.16480v1 Announce Type: cross Abstract: We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-languag
arXiv:2608.14212v1 Announce Type: new Abstract: As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rat
EXL3 is an alternative to llama.cpp. And while there is extensive tooling for llama.cpp, EXL3's primary deployment (TabbyAPI), has a OpenAI compatible API so it shouldn't matter. Why won't this tool m
arXiv:2204.13805v5 Announce Type: replace-cross Abstract: Gender gaps in how scientific work is evaluated are well documented, but their sources remain debated. We ask whether an overlooked factor---t
arXiv:2608.14068v1 Announce Type: cross Abstract: Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a
https://github.com/alekk89/llama-cpp-windows-manager It has been three months since I first shared my personal solution for running llama.cpp on Windows, and the project has evolved considerably since
arXiv:2407.13911v5 Announce Type: replace Abstract: Prompt-based continual learning has shown strong performance in rehearsal-free class-incremental learning by adapting learnable prompts while freezi
arXiv:2608.12385v1 Announce Type: new Abstract: As large language models serve more requests, cumulative inference cost is becoming increasingly important relative to one-time training cost. The two i
arXiv:2608.12514v1 Announce Type: new Abstract: Deep graph neural networks(GNNs) suffer from oversmoothing- a progressive collapse of node representation towards a low information subspace as network
arXiv:2608.12611v1 Announce Type: new Abstract: Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible detai
arXiv:2606.13172v3 Announce Type: replace Abstract: Learned representations are central to modern machine learning and are typically evaluated through predictive performance, robustness, uncertainty e
arXiv:2608.12149v1 Announce Type: new Abstract: We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two architecture-aligned morphologies: MAs
arXiv:2608.12314v1 Announce Type: new Abstract: Previsualization is an intermediate layer between ideas and production in film, games, architecture, and urban design. It lets creators iteratively refi
arXiv:2608.10760v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has become the de-facto interface for connecting LLM agents to enterprise tools, and adoption has been explosive: wit
arXiv:2608.10756v1 Announce Type: cross Abstract: Embodied mobile manipulation requires language, visual observations, three-dimensional scene structure, and action feasibility to be aligned before ex
arXiv:2608.10795v1 Announce Type: new Abstract: Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may tran
arXiv:2608.10676v1 Announce Type: new Abstract: Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments. However, providing complete
arXiv:2608.10258v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do
arXiv:2608.08689v1 Announce Type: new Abstract: The state evolution of a complex system arises jointly from object laws, relational propagation, domain conservation, and unmodeled error. Forcing all s
Back after ~6 months — rebuilding my spiking language model around CPU-first inference Hey everyone. It’s been around six months since I last posted anything about this project here. Some of you might
arXiv:2608.08949v1 Announce Type: new Abstract: Dense 3D reconstruction is critical for clinical endoscopic navigation and documentation. While Gaussian Splatting SLAM systems show promise in this dom
GitHub: https://github.com/xmarre/ComfyUI-DoRA-Dynamic-LoRA-Loader Release v1.0.39: https://github.com/xmarre/ComfyUI-DoRA-Dynamic-LoRA-Loader/releases/tag/v1.0.39 Also available through ComfyUI Manag
arXiv:2608.07544v1 Announce Type: cross Abstract: Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs). Yet
arXiv:2608.09218v1 Announce Type: new Abstract: Score-driven filters multiply a scaled log-likelihood score by a gain that controls the update magnitude. We treat this gain as a decision variable and