Search: “gpt”

arXiv:2610.14350v1 Announce Type: cross Abstract: Having demonstrated a strong potential for automating vulnerability discovery, AI agents can also be used to attack software systems at scale. Today's

New impressive work from Microsoft and collaborators. And it's one of my favorite recent topics: RL environments. They show that Qwen3.6-35B-A3B goes from 41.1 to 53.3 on Terminal-Bench 2.1 by trainin

arXiv:2610.14344v1 Announce Type: new Abstract: Scaling deep learning models efficiently requires predictable performance transfer across compute regimes. Establishing reliable hyperparameter transfer

arXiv:2610.14043v1 Announce Type: cross Abstract: Frontier language models reliably refuse to explain how to cause physical harm. We ask whether this refusal survives when the same models control a ro

arXiv:2610.17426v1 Announce Type: new Abstract: Clinical decision-making is a sequential process of information collection, clinical inference, and forecasting under partial observability, often witho

tl;dr: new qwen finetune that simultaneously pushes the frontiers of small model capability and reasoning efficiency. Hey everyone, We publish two post-trained versions of Qwen 3.8 27B called Sabi-Noe

arXiv:2610.16957v1 Announce Type: cross Abstract: Standard hate speech detection datasets often emphasize explicit harmful language, but directed harm can also be expressed indirectly, without clearly

arXiv:2610.18868v1 Announce Type: cross Abstract: Long-horizon agents have drawn growing attention for their ability to work autonomously -- from hours to days -- on economically valuable tasks, a cap

arXiv:2610.17242v1 Announce Type: new Abstract: Can a vision-language model tell left from right? Modern VLMs solve visual puzzles and follow hour-long videos, yet when asked whether the camera moved

arXiv:2610.17285v1 Announce Type: new Abstract: Modern neural-network training uses mixed recipes, assigning AdamW-like or sign-based updates to embedding and output layers and spectral updates to hid

Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become training data for the mode

Every few weeks, a new model steps up and claims best-in-class at something. The launch chart makes the case, the link makes the rounds, and your team is back to the question nobody has time for: shou

Robert Hart / The Verge: Google rolls out Gemini 4 Argon globally via the Gemini API and to Google AI Pro subscribers in the Gemini app and AI Mode, and in Antigravity for Ultra users — After months o

Redesigning source control at Anthropic Interesting piece from Anthropic describing why and how they built their own custom alternative to Git, based on the dramatic increase in rate of changes to the

router lives in the harness, not a gateway, bc the harness knows the task blog: https://www.langchain.com/blog/how-to-build-a-model-router-in-the-harness https://x.com/neil_xbt/status/2109979966859510

arXiv:2606.19386v2 Announce Type: replace-cross Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in ou

arXiv:2610.13025v1 Announce Type: new Abstract: Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improve

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

arXiv:2610.12987v1 Announce Type: new Abstract: If a second text corpus were collected from the same population, how much would a predictor's outputs change? We study this question for masked-text rec

arXiv:2610.12669v1 Announce Type: cross Abstract: Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. Th

Hey everyone, I made whatmodel.sh To use it, Enter your RAM and GPU See what models you can run locally with its rank and the command to run it Compare them with API models on the same score Building

arXiv:2610.12989v1 Announce Type: new Abstract: We investigate whether language models contain internal components that contribute to representing narrativity, the degree to which a text exhibits narr

arXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Me

Release: llm-meta-ai 0.2 Meta AI release Muse Wonder (and Muse Wonder Full), their new 'most capable models'. These look like they may be Meta's first Fable class models - Artificial Analysis scores M

arXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-

arXiv:2610.12659v1 Announce Type: new Abstract: Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether

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:2610.12954v1 Announce Type: new Abstract: This paper introduces MathVis, a benchmark designed to evaluate LLMs' ability to visualize frontier mathematical problems and perform diagram-assisted r

New Show Announcement: High Taste Testers Good food and good ai convos Pilot episode 🔜 http://youtube.com/@latentspacepod ft: @davis7, @dexhorthy @AdjectiveAllison, @altryne, @benhylak on DevDay/Dots,

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:2505.17244v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) leverage explicit reasoning traces, known as Chain-of-Thought (CoT) reasoning, to decompose complex problems int

arXiv:2610.03994v2 Announce Type: replace-cross Abstract: VeriContest is a benchmark of 1007 competitive-programming problems in Rust, each with a Verus specification, a judge-accepted solution, and a

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

If you build on open-weight reasoning models, you have probably wanted a 'how sure is the model about this answer?' signal that does not cost 5x sampling, a judge model, or a labeled dataset. Hence, w

arXiv:2610.12707v1 Announce Type: cross Abstract: Vision-language reward models are trained on annotated preference pairs, which are expensive to collect, can disagree, and are ranked by benchmark acc

arXiv:2610.13098v1 Announce Type: new Abstract: Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous su

Release: web-edit 0.1a0 I was working on a project from my phone using Codex Remote when I found myself wanting to edit a credentials file without round-tripping those credentials through the LLM itse

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

One of the biggest historical bottlenecks for training specialized models has been curating ground-truth. This is typically a very labor intensive process done with human supervision. Now frontier mod

webAI released TwIL LM3 Pro on September 30. I haven't seen it posted here yet, so I went through the model card, and their comparison chart is attached. It's a 3.66B model built on IBM's Granite 4.2

For what it's worth. I'm a mechanical engineer by education and software engineer in practice over the past ~20 years. Playing around with local models has been a recent hobby. Today I decided to do a

arXiv:2610.12183v1 Announce Type: cross Abstract: Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large la

arXiv:2610.11436v1 Announce Type: new Abstract: An answer judge instructed to grade the final commitment should reject an explicitly wrong final value even when an earlier value matches the reference.

arXiv:2610.11050v1 Announce Type: new Abstract: Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for eva