Search: “claude”

arXiv:2609.34460v1 Announce Type: cross Abstract: Does structured mathematical knowledge help LLMs prove theorems in Lean 4? If so, for which models, and does the answer vary by problem? Formal librar

arXiv:2609.36550v1 Announce Type: new Abstract: Retrieval-augmented generation is widely used in professional writing, yet whether retrieval grounds revision or merely injects templates is rarely test

Hybrid search, reranking, query decomposition, and query expansion are often treated as must-haves for good RAG. We wanted to see how much each actually helped, so we tested them. Same model, same emb

arXiv:2505.21870v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) generally enhances large language models' (LLMs) ability to solve knowledge-intensive tasks. But RAG coul

arXiv:2610.08205v1 Announce Type: cross Abstract: Assistants grounded in a small, frequently edited knowledge base can retrieve through tool calls to a live data interface or through vector retrieval-

Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully curate the papers, so you can expect mostly bangers. The index

Explore the top AI papers of the week with our brand-new MCP tools. Connect it to Codex, Claude Code, or Grok Bot. Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to

Here're results from my final test of coding, coding (panda/numpy), data analysis, data-driven decision-making, and local RAG domains I interact with most often. This test, which is refined from a 500

separating artifacts from the agent makes sense for sharing and cross-AI collaboration No vendor lock-in for your artifacts. Sites, decks, 3D games, reports, dashboards and galleries. Artifacts on Fly

arXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggreg

arXiv:2610.13563v1 Announce Type: cross Abstract: Repository-level issue-resolution benchmarks such as SWE-bench evaluate submitted patches primarily based on whether they pass the correctness tests,

arXiv:2610.13330v1 Announce Type: new Abstract: Designing tool-integrated reasoning agent systems for complex chemical tasks remains a fundamental challenge. Although recent chemical agents have demon

arXiv:2610.13075v1 Announce Type: new Abstract: Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Exi

You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa

At AI Engineer New York 2026, Anthropic introduced **dynamic workflows** (also called “flows”), a new type of multi‑agent orchestration designed for large, ambitious workloads using Claude Managed Age

arXiv:2610.12789v1 Announce Type: new Abstract: Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can

Introducing River Recipes: our open-source initiative for turning promising research into vetted, reproducible training recipes. Our first recipe tackles text-to-SQL, where our trained open models bea

(Don't judge by the screenshot, the cache is cold. It hits 24+ tok/s with a warm cache!) About two months ago, I made a post here asking whether predicting which MoE experts would be used on the next

Finetuned Qwen3.5-4B into a decision model like Jev using @UnslothAI. - 4-bit QLoRA, bf16, single A100, 15 min. - Train/val loss flatten after 2 epochs so most of the learning happens fast. - Trained

We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models, at much lower cost and speed, for a specialized task (fraud

With only ~$1,000 of training compute, we trained 𝗳𝗿𝗼𝗺 𝘀𝗰𝗿𝗮𝘁𝗰𝗵 a 1.7B coding agent that beats Claude 3 Opus and GPT-4o on SWE-bench Verified 🤯 At 25.5% pass@1, it sets a new record for nanoswe, our op

Here're results from my final test of coding, coding (panda/numpy), data analysis, data-driven decision-making, and local RAG domains I interact with most often. This test, which is refined from a 500

arXiv:2610.13330v1 Announce Type: new Abstract: Designing tool-integrated reasoning agent systems for complex chemical tasks remains a fundamental challenge. Although recent chemical agents have demon

You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa

managed deep agents 0.9 is here! things we shipped: ⏰ agents can schedule tasks OBO themselves or the user 🏭 dynamically configure your mda per run (models, tools, skills, etc.) 👀 Slack reactions show

Editor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your

arXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges tak

I've been building ANCHOR, a web automation agent that runs entirely on Ollama. You describe a task in plain language ('Register Maria Silva, IT department, contractor, and save'), point it at a site,

arXiv:2610.11233v1 Announce Type: cross Abstract: A core challenge in short-video fact-checking is identifying which evidence is sufficient to support a verification conclusion. Existing approaches ei

arXiv:2610.11402v1 Announce Type: new Abstract: GoldenViewVQA requires models to jointly answer driving-scene questions and identify the camera view containing the supporting visual evidence, making p

arXiv:2610.11963v1 Announce Type: cross Abstract: A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adj

arXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggreg

arXiv:2610.03585v1 Announce Type: cross Abstract: Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare d

The 'old' version of Cowork runs model inference in the cloud, executing tool calls in an Anthropic-provided VM we shipped to your computer. We added the VM for capability, safety, and security reason

arXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources

I wanted to build an offline bird/plant identifier that runs on a laptop with Ollama. Before building any UI, I tested it on 6 photos: Common Myna → gemma4:e2b said 'Jackdaw' (confidence: high). gemma

An interesting cognitive bias: 'GLM 5.3 is around as capable as Claude Mythos at cyber-exploitation while also having much lower safeguards, meaning that every additional day absent some dire cybersec

Editor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your

Hayden Field / The Verge: Anthropic updates its usage policy to ban “sustained and needless abusive or cruel behavior” toward Claude; ending chats is “the primary enforcement mechanism” — The usage po

1/ My heart is heavy. I made a number of mistakes in my life, and not asking earlier for an immediate slowdown is one of them. If OpenAI starts making similar breakthroughs in biology, we risk somethi