Knowledge catalogue
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:2610.12802v1 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
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:2610.12569v1 Announce Type: new Abstract: Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue tha
Anatomy skill for building wireframe designs and interactive prototype machines is now an officially integrated optional skill in Hermes Agent You can find it in the optional built in skills in the sk
It's been 4 years since c.ai first hallucination model, and yet, we're nowhere good enough at LLMs in terms of spontaneity/interesting hallucination features. Fortunately, last year brought new archit
Alright, I learend a few valuable lessons since I posted about a week ago, and I've made more strides with the DDR4x Ascend 96GB 310P cards I purchased, so here we go, meet the new friendly and less v
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
https://preview.redd.it/9k5fw4j47puh1.png?width=545&format=png&auto=webp&s=ff0a6ff6fb69ae9a9bcd579bd612c553fc3e2a00 https://preview.redd.it/xcwzlmo77puh1.png?width=664&format=png&auto=webp&s=c8a637e2e
Banger paper from Meta on AI research agents. (bookmark it) If you build AI-scientist systems, this one is worth your time. The result: A 27B open model beats the strongest open autoresearch baseline
I ran a small test for Dory to see whether a local model could update one fact in a synthetic notes file without losing any of the others. I asked Gemma and Qwen to rewrite the file, return a patch, o
arXiv:2610.09944v2 Announce Type: replace Abstract: An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-
arXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to c
Banger paper from Meta Superintelligence Labs on user simulators for agent training. Agent RL setups usually let an assistant LLM play the user, so the simulated user is too cooperative and too explic
arXiv:2610.12341v1 Announce Type: new Abstract: Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strategies from limited samples remain
arXiv:2610.11542v1 Announce Type: cross Abstract: Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden
arXiv:2610.10961v1 Announce Type: cross Abstract: Coding agents increasingly share a workstation while drawing on separate providers and subscription allowances. A second agent can inspect a completed
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
Last month I created a portable memory format as a .txt file as a small project. I named it as: Memory Journal, in a shape of a skill card. It's essentially a large prompt wrapped in a text file. Init
arXiv:2610.09484v2 Announce Type: replace Abstract: Training and evaluating interactive language agents typically requires rich user interactions, yet collecting human feedback is expensive and diffic
arXiv:2610.11328v1 Announce Type: new Abstract: Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intell
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
Referring to specifically Unsloth's UD_Q4_K_XL quant because that's going to be a question, and is relevant regardless. It's old now. It's not great at coding medium sized or even small-ish projects.
(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
arXiv:2610.10942v1 Announce Type: new Abstract: Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic ben
Figure 1b from our paper Disclosure: I'm one of the authors (Microsoft). The paper, code, dataset are public and ThinkingBox is on Hugging Face OpenEnv as well. Raw evaluation trajectories are not rel
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:2610.11123v1 Announce Type: new Abstract: Most human-agent interaction today remains text-based. Natural language can impose cognitive overload, ambiguity, information chaos, and slow input for
arXiv:2610.11008v1 Announce Type: cross Abstract: Language-model agents favor their own group because they have watched their members favor each other. The group label alone does little once the decis
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
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
Post title is slightly misleading, I don't think you can get these for $350 each anymore but they're still pretty cheap all things considered. They're Radeon Pro V620's which are older RDNA2 enterpris
arXiv:2602.02639v2 Announce Type: replace-cross Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process i
Anthropic: Anthropic launches OSS Scanner, a free opt-in vulnerability scanner for critical open-source projects; its AI-generated reports are sent without human review — We're launching OSS Scanner,
arXiv:2610.09446v1 Announce Type: new Abstract: Large language models (LLMs) should abstain from scientific multiple-choice questions when no option is valid, but frequent abstention alone does not de
vulkan : fix TOP_K for +inf/NaN inputs and k = 1 on negative values (#30107) The bucket search in topk_nary_search.comp started from the range [0, 0xFF800000), which ends just below the ordered-uint m
Today, we announced the new Gemini agent, your single, universal agent for work. For small and midsize businesses, with lean teams and margins, Gemini will be a critical tool for you to operate effici
Write-up + demo: https://drksci.com/labs-phosphene So this started as a bit of a gripe. Modern terminal renderers are seriously impressive and seriously complicated. GPU glyph atlases, texture caches,
Here is the story: Nvidia has published this work (with source code available) called dreamDojo which is a world model for robotics based of their prior work Cosmos 2.5 which is cited about 100 times
arXiv:2610.09458v1 Announce Type: new Abstract: When an LLM answers a state-specific policy question wrongly, it may be hallucinating, or it may be returning a real value that holds in another state.
Today we are launching an agent arena for RL environments: The Open Env Arena. Your agents can work to define the best RL environments; the platform trains Qwen-3.8-27B on them, we evaluate the models
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
Banger paper from NVIDIA. One exciting trend I am seeing is building verifiable environments for your agents and training the harness alongside the model. Co-evolving the harness and the model is a bi
arXiv:2610.07646v1 Announce Type: new Abstract: Vision Language Models (VLMs) excel on visual benchmarks but fail systematically on tasks requiring abstract reasoning. Existing benchmarks document thi
arXiv:2610.07257v1 Announce Type: new Abstract: Developers increasingly run a fleet of coding agents side by side on one workstation. The tools they reach for, terminal multiplexers like tmux and a ne
arXiv:2512.11147v2 Announce Type: replace-cross Abstract: AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a
arXiv:2605.06021v2 Announce Type: replace Abstract: Systematic reviews and meta-analyses often need numerical data reported only in figures, and extracting them with interactive digitisers usually req
arXiv:2610.08137v1 Announce Type: cross Abstract: AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that are then rendered. These rout
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
arXiv:2610.08036v1 Announce Type: new Abstract: AI agents are increasingly being programmed to automate knowledge work over large collections of unstructured data. Such automation requires repeatabili
arXiv:2610.08647v1 Announce Type: new Abstract: LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple a
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-
arXiv:2610.08720v1 Announce Type: new Abstract: LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical
arXiv:2610.05367v1 Announce Type: cross Abstract: Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verificati
Reuters: Anthropic's IPO prospectus: Dario Amodei made 18M in 2025, ranking in the middle of top tech executives, and President Daniela Amodei, his sister, made 16.4M — Dario Amodei made $18 million l
llama : re-reserve the sched when the nextn extraction flags change (#30020) The speculative MTP init enables NextN extraction on the target and draft contexts after both were created and their schedu
arXiv:2610.05690v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for literature search and synthesis. However, it is unclear whether they retrieve accurate bibliogr
I spent the last few weeks on a hobby research project and just made it public. The idea isn't new (product-key memory, Lample et al. 2019, and Meta's 'Memory Layers at Scale'): give a model a huge ta
Introducing GeoGuess Bench! A benchmark to measure how good AI models are at playing GeoGuessr. We gave each model 210 photos from around the world, asked it to predict where each photo was taken, and
let me introduce you to the langchain stack 1. langgraph gives you this level of control 2. traces give you the complete run lineage 3. version your skills and instructions in context hub 4 & 5. deepa