AI infrastructure
27 notes, newest first. Includes the vault tags infrastructure, ai infrastructure, gpu, hardware, energy.
nanoMuse: An Open-Source Personal Agent for Every Device You Own
The preprint presents nanoMuse as an open-source counterpart to persistent personal agents that operate across a user's accounts and devices. It describes a shared conversation over a user-runnable relay, a Sentinel…
Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?
The preprint introduces BOTTLED, a benchmark in which agents receive an unlabelled workload and must complete it under fixed time, compute, and LLM API budgets. Agents may train a small model or write a reusable…
SquidAgent: Parallelize Wisely, Coordinate Efficiently
The preprint identifies re-exploration and alignment as hidden costs that can make parallel multi-agent systems slower than a single-agent baseline. It proposes a token-based decision criterion, direct forking from the…
Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving
The preprint proposes HEAR, a bidirectional Harness–Engine Pairing protocol that lets an agent harness communicate workflow intent and execution requirements while the inference engine returns runtime state…
ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement
The preprint describes an autonomous post-training harness that attributes errors, selects update directions, and executes model updates under a limited compute budget. It combines metric- and case-level analysis…
Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints
The preprint proposes the Homomorphic Advantage Operator to stabilize deep reinforcement learning when nonlinear operations are approximated under fully homomorphic encryption. It applies a zero-mean centering…
You Cannot Pick a Provider From the Price List: Market-Aware Routing for Open-Weight LLM Inference
The preprint argues that open-weight inference routing must choose both a model and the provider serving it. Across live endpoints, models, task types, and three measurement waves, it reports that the same model can…
Report: Progressive Disclosure of Agent Skills
The report describes a Workday deployment context in which named procedures, or skills, are added to an LLM agent's context. It evaluates progressive disclosure (lazy-loading) of skills as a way to control the cost of…
CompKV: Compensation-Aware KV Selection for Long-Context LLM Inference
CompKV selects token blocks jointly with the downstream compensation mechanism for sparse attention rather than choosing tokens only by attention mass. The preprint derives a block-level residual approximation based on…
SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
SWE-Serve contains 53 repository-grounded tasks derived from production changes to SGLang, spanning six inference-engineering families. Tasks use hidden functional and regression tests, end-to-end serving tests…
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
The record describes a 552B-backbone multimodal mixture-of-experts model with up to one million tokens of context, activating 16B parameters during decode and 8B during prefill. It reports cross-layer KV reuse, FP4 KV…
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Video DeltaNet combines local Softmax attention with bidirectional linear memory for long-range video context. Its Video Delta Attention updates memory once per frame, with separate projections and gates for…
Could Underwater Data Centers Pose a Risk to AI Treaty Verification?
The paper evaluates whether underwater data centers could conceal a 100,000-H100-equivalent training run. It reports that power and cooling are tractable, while interconnect and hands-on maintenance are severe…
Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages
The authors discuss how the underlying infrastructure of AI tools designed for education and language support can disadvantage speakers of underrepresented languages, using Bengali as an example. They highlight four…
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
The paper argues no single LLM is optimal for every query or budget, and proposes a standard framework plus open-source toolkit for building, testing, and deploying systems that route each query to the most suitable…
LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications
This paper discusses how large language models (LLMs) and agentic AI systems are being used in smart grids for tasks like forecasting, optimization, and control. The authors present a design principle called the…
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
The text is about AgentCompass, an open-source evaluation infrastructure designed to evaluate Large Language Models (LLMs) as they evolve into autonomous agents. The infrastructure aims to address the current…
Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
Researchers propose a new method for feature selection in renewable energy prediction pipelines, called Cluster-based Sequential Feature Selection (CSFS). This method aims to address the gap in limited or unsystematic…
A Multimodal Dataset for Large Language Model Applications in the Energy Domain
The paper introduces a new open-access dataset called mAIEnergy which is a multimodal corpus designed to support Large Language Model (LLM) applications in the energy sector. It contains various types of data including…
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
The paper proposes SolarChain-Eval, a benchmark to evaluate the trustworthiness of economic agents in decentralized energy markets using a physics-constrained Markov Decision Process. The benchmark evaluates agents'…
Adaptive Inference Batching using Policy Gradients
The paper investigates using reinforcement learning (RL) to create adaptive batching and routing policies for inference serving systems that can handle bursty, heterogeneous workloads. The research finds that in…
Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
The paper proposes a hardware-enforced semantic coordination architecture for safety-critical real-time autonomous systems. This approach aims to overcome limitations of software-mediated coordination by implementing…
State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading
Researchers studied the impact of state representation in deep reinforcement learning (DRL) for energy trading decisions, using a fixed Double DQN agent in the HydroDam environment. They found that combining absolute…
State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading
Researchers compared different methods for representing market conditions in reinforcement learning (RL) models for energy trading. They found that combining multiple types of features led to stronger performance…
Shared Infrastructure, Isolated Tenants: Pool Model Multi-Tenancy with Amazon Bedrock AgentCore
AWS demonstrates production-ready multi-tenant AI agent patterns using Bedrock AgentCore, illustrated through a healthcare use case serving multiple clinics and hospitals. The post covers pool model multi-tenancy with…
Temporary Cloudflare Accounts for AI Agents
Cloudflare launched Temporary Accounts on Workers, allowing AI agents to deploy a live Worker in seconds via wrangler deploy --temporary. This enables ephemeral compute resources for agents without requiring persistent…
Amazon Bedrock AgentCore Harness Is Now Generally Available
AWS announced general availability of Amazon Bedrock AgentCore Harness, enabling simplified production-grade agent creation from minimal code. The announcement claims agents can be deployed "from idea to…
