Knowledge catalogue
arXiv:2610.07557v1 Announce Type: cross Abstract: Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and re
arXiv:2610.07816v1 Announce Type: new Abstract: Small language models (SLMs) are attractive as local agent controllers because they reduce remote inference, latency, and deployment footprint, yet stru
arXiv:2610.08662v1 Announce Type: new Abstract: As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing
Disclosure first: I work at Vstorm and I build AgenticOS, an open-source (Apache-2.0), self-hosted platform for building AI agents in a browser. This post was drafted with an LLM's help and edited by
Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API, as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin for talking to Jev, I
arXiv:2610.04432v1 Announce Type: new Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on manu
arXiv:2610.01618v1 Announce Type: new Abstract: Agent evaluations increasingly go beyond a single success rate, reporting metrics such as cost, consistency, and robustness. Yet they typically treat th
I've been experimenting with running larger models locally with Ollama, mainly because I'm interested in using them for agentic coding. I kept seeing benchmarks expressed as something like: 40 tokens/
arXiv:2610.00313v1 Announce Type: new Abstract: Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to
arXiv:2610.00650v1 Announce Type: cross Abstract: The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted an
arXiv:2609.39957v1 Announce Type: cross Abstract: Coding agents solve repository-level tasks through sequences of actions, where a single erroneous action can misdirect subsequent decisions and increa
arXiv:2609.36777v1 Announce Type: new Abstract: Frontier coding agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely cont
arXiv:2609.33762v1 Announce Type: cross Abstract: LLM agents resend their whole conversation on every turn, and most of it was already processed on the previous turn. Serving systems avoid recomputing
I'm at OpenAI DevDay today, in Fort Mason, San Francisco. Same as last year I'll be live blogging the keynote and some other notes during the day. OpenAI gave me a free ticket and a seat in the 'creat
arXiv:2609.35143v1 Announce Type: new Abstract: AI agents increasingly carry out long-horizon professional work, but their evaluations rarely require a finished creative deliverable. To this end, we i
arXiv:2609.26891v1 Announce Type: new Abstract: Modern language-model agents are built around the extit{agent loop}, where the LLM is placed in an environment exposing a set of tools, and the LLM has
The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking their full potential requir
arXiv:2609.26499v1 Announce Type: new Abstract: Today, progress in open-weight language models enables systems capable of writing, executing and debugging code while still running on a single workstat
SF October 14th: A Birds of a Feather Session on Agentic Engineering I'm hosting an evening event with Jesse Vincent in San Francisco on Wednesday 14th October for people who are building weird and in
Retrieval benchmarks sometimes feel benchmaxxed by models, so we wanted to find a way to tie it as close as possible to my objective: finding the article that answers a product question right. We work
Release: llm-keys-ui 0.1 This plugin solves a very specific problem. I've started using Codex Remote to run coding agents on various machines while controlling them from my phone. Sometimes I use thos
Been integrating Jev into my custom harness. I couldn't be more excited about the results I am seeing. Most demos on my timeline are flashy but very basic. Notice they are all about some boring classi
MiniMax has released the source code for MiniMax Code’s terminal agent: https://github.com/MiniMax-AI/minimax-code https://preview.redd.it/st9izmm8zaqh1.png?width=3016&format=png&auto=webp&s=5853bc316
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. AGENTS.md support is built off of C
arXiv:2609.17652v1 Announce Type: cross Abstract: When agentic sessions run to a million tokens with many sessions resident at once, the KV cache and the index that ranks it live in host memory, and t
arXiv:2609.18805v1 Announce Type: cross Abstract: Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web development, however, agents ma
Things to try with Jev right now: 1. LLM-as-a-Judge evaluation 2. Routing for agent harnesses harness 3. Scaling agent orchestration by enabling smarter subagent creation with SOTA classification capa
arXiv:2609.16302v1 Announce Type: cross Abstract: When a coding agent returns to existing software, it inherits evidence from earlier engineering work: tests, type checks, proofs, static analyses, and
arXiv:2511.20109v2 Announce Type: replace Abstract: Climate science demands automated workflows to transform comprehensive questions into data-driven statements across massive, heterogeneous datasets.
arXiv:2606.22906v2 Announce Type: replace-cross Abstract: Large language models have shown strong performance on software engineering (SE) tasks, yet understanding large industrial repositories remain
arXiv:2609.14857v1 Announce Type: new Abstract: Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution
I’ve been building Catalyst around a capability I want engineering agents to have: An AI agent can read a program and make a good guess about what matters. Catalyst lets it measure what actually matte
Learn to build a harness, folks. It's not surprising to me that so many YC builders want to build domain-specific harnesses. If you work long enough on a domain-specific problem, you quickly realize t
arXiv:2609.05527v1 Announce Type: new Abstract: Wherever a coding agent works under engineer supervision, or a clinical model assists a radiologist, the deployment question is whether to keep the huma
First off, I'm super thankful for the value Ollama has given me Got me setup with my first local LLM setup (early OpenClaw days amirite!?) Then got me into their 20 plan and what really sold me here w
Native is now the future of mobile at Shopify Shopify are moving from React Native back to separate Swift and Kotlin codebases for their native apps, for the exact reason you would expect: We decided
arXiv:2609.08175v1 Announce Type: new Abstract: Harness self-evolution is the process by which an agent modifies its prompts, tools, code, or orchestration in response to task feedback while keeping t
arXiv:2609.07785v1 Announce Type: new Abstract: An LLM-agent leaderboard invites a familiar inference: an agent ranked above another is the better agent. Public evaluation logs may not support that co
Tool: .blend URL Viewer I'm continuing to have a lot of fun with GPT-6 Astra and Blender (see my TIL). As a big fan of the Imperial Fabergé Easter eggs, I've always thought it would be fun to make som
// From Language Models to World-Acting Systems // A critical review of agentic AI, and a framework that is genuinely useful for deciding how much authority to hand an agent. Here is how it works. The
Research acceleration: The view inside OpenAI Apparently today is RSI day at OpenAI, for Recursive Self-Improvement - I think it's their new AGI. Both this piece and the new essay An Alien Mind (by Ch
TIL: Using Blender with coding agents on macOS I've been having fun with Blender in ChatGPT Codex on my Mac recently. Getting it to work with coding agents is really easy: install the full Mac applica
arXiv:2609.04167v1 Announce Type: cross Abstract: Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measur
arXiv:2609.01861v1 Announce Type: new Abstract: The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an opti
arXiv:2609.00365v1 Announce Type: new Abstract: Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fra
arXiv:2609.01481v1 Announce Type: new Abstract: This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and us
arXiv:2609.00453v1 Announce Type: new Abstract: Giving an agent a file about a named expert can supply hard-to-find material, produce a recognizable persona, or change what the agent decides. These ar
Not all harnesses are created equal. And there is no one-size-fits-all. A good harness should solve your context engineering problems. Understanding and optimizing lower-level details like system prom
Direct2D has always been the biggest hurdle for Paint.NET on WINE, and it's clear that it will never be completed enough for Paint.NET's use. And I can't just 'disable' the use of Direct2D. So, instea
arXiv:2609.00643v1 Announce Type: new Abstract: Agent revisions expose a fundamental correctness--efficiency trade-off during concurrent execution. Discarding ongoing work preserves latest-version cor
Why I have this data: one Pro account kept hitting limits, so I run three Pro subs through 9router, a self-hosted router that sits between my coding tools and ollama cloud. It spreads requests across
arXiv:2608.31057v1 Announce Type: new Abstract: Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles an
Atlassian uses Claude for complex Rovo workflows and Claude Code internally; its multimodel platform also uses Google Cloud.
Just a rumour of a bug is enough to find a security exploit these days Anil Madhavapeddy is a professor of computer science at Cambridge and a core maintainer of the OCaml compiler. In this somewhat a
This is as bad as saying there is no alpha in customizing your own models. I don't think people realize how much harnesses and models go hand in hand. And thus the rest of the intelligence stack. Not
arXiv:2608.24188v1 Announce Type: new Abstract: Coding agents re-send large file reads and tool outputs to a frontier LLM every turn, and this context dominates their token bill. General-purpose promp
The fact that AI wrote 1M LOC and then refined it over the course of the next couple of months to produce a reliable piece of software that is currently running on millions of developer machines is ab
Impressive new paper from Microsoft and colleagues. Harness design is still hand-tuned almost everywhere. This work present an automated loop to optimize the harness. They introduce AutoSaddler, which
arXiv:2608.23552v1 Announce Type: new Abstract: Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context
arXiv:2608.21929v1 Announce Type: cross Abstract: Agent skills extend coding agents with task-specific instructions, scripts, and resources, but they also create a trusted instruction channel that can