May 2026

arXiv:2605.13850v1 Announce Type: new Abstract: Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology — how data flows — while cognitive science surveys focus on cognitive function — what the agent does. Neither axis alone disambiguates architecturally distinct systems: the same Orchestrator-Workers topology can implement Plan-and-Execute, Hierarchical Delegation, or Adversarial Verification — three patterns with fundamentally different failure modes and design trade-offs. We propose a two-dimensional […]

Ver mais

arXiv:2605.13849v1 Announce Type: new Abstract: Determining what to eat to satisfy nutritional requirements is one of the oldest optimization problems in operations research, yet existing formulations have two persistent limitations: continuous variables produce impractical fractional servings (1.7 eggs, 0.37 bananas), and hard nutrient constraints cause infeasibility when targets conflict. A systematic review of 56 diet optimization papers found that none combine integer programming with goal programming to address both issues. We propose Mixed Integer Goal Programming (MIGP) for […]

Ver mais

arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce GraphBit, an engine-orchestrated framework that defines workflows explicitly and deterministically as a directed acyclic graph (DAG). Unlike prompted orchestration, agents in GraphBit operate as typed functions, while a Rust-based engine governs routing, state transitions, and tool invocation, ensuring reproducibility and auditability. The engine supports parallel branch […]

Ver mais

From Thomas G. Dietterich (arXiv moderator for cs.LG) on 𝕏 (thread): https://x.com/tdietterich/status/2055000956144935055 https://xcancel.com/tdietterich/status/2055000956144935055 “Attention arXiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. If generative AI tools generate inappropriate language, plagiarized content, biased content, errors, mistakes, incorrect references, or misleading content, and that output is included in scientific works, it is the responsibility […]

Ver mais

Example 1: The Viking 1 lander In the 1970s, NASA sent a pair of probes to Mars, the Viking 1 and Viking 2 missions. Total cost of $1B (1970), equivalent to about $7B (2025). The Viking 1 probe operated on Mars’s surface for six years, before its battery began to seriously degrade. One might have thought a battery problem like that would spell the irrevocable end of the mission. The probe had already launched and was now on […]

Ver mais

Release: datasette-llm-limits 0.1a0 This plugin works in conjunction with datasette-llm and datasette-llm-accountant to let you configure a per-user (or global) spending limit for LLM usage inside of Datasette. Configuration looks something like this: plugins: datasette-llm-limits: limits: per-user-daily: scope: actor window: rolling-24h amount_usd: 1.00 Tags: llm, datasette

Ver mais

Pre-training large language models is expensive enough that even modest efficiency improvements can translate into meaningful cost and time savings. Nous Research is releasing Token Superposition Training (TST), a method that substantially reduces pre-training wall-clock time at fixed compute without touching the model architecture, optimizer, tokenizer, parallelism strategy, or training data. At the 10B-A1B mixture-of-experts scale, TST reaches a lower final training loss than a matched-FLOPs baseline while consuming 4,768 B200-GPU-hours versus the baseline’s 12,311 — roughly a […]

Ver mais

Cline became ‘agentic’ before it was cool, but building on the bleeding edge usually leads to some structural debt. Over time, the agent loop and the VS Code extension became a package deal—making it a headache to maintain or move to new environments. Its tough to just keep layering features on a rigid core. Cline, the open-source AI coding agent used by millions of developers, shipped a significant architectural change this week: it extracted its internal agent harness […]

Ver mais

In this tutorial, we delve into CuPy as a powerful GPU-accelerated alternative to NumPy for high-performance numerical computing in Python. We start by inspecting the available CUDA device, checking the CuPy version, runtime details, GPU memory, and compute capability so that we understand the hardware environment before running heavy computations. Then, we compare NumPy and CuPy on large matrix multiplication and FFT workloads to see how GPU acceleration changes execution speed. Also, we work with memory pools, custom […]

Ver mais

This Mitchell Hashimoto quote about Bun migrating from Zig to Rust reminded me of a similar conversation I had at a conference last week. I was talking to someone who worked for a medium sized technology company with a pair of legacy/legendary iPhone and Android apps. They told me they had just completed a coding-agent driven rewrite of both apps to React Native. I asked why they chose that, given that coding agents presumably drive down the cost […]

Ver mais