Redesigning source control at Anthropic
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
Knowledge catalogue
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
arXiv:2510.10998v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hir
arXiv:2610.13273v1 Announce Type: cross Abstract: API specifications serve as critical documentation for modern software development, directly impacting integration efficiency and client code generati
arXiv:2610.13455v1 Announce Type: new Abstract: Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has
arXiv:2610.13354v1 Announce Type: new Abstract: The NIST Assembly Task Board #1 remains a challenging benchmark for learning-based methods in robotic manipulation. Over short horizons, it demands prec
arXiv:2610.13891v1 Announce Type: cross Abstract: Light Detection and Ranging (LiDAR) is critical for autonomous perception, yet its performance is known to degrade in adverse weather. While existing
arXiv:2610.12792v1 Announce Type: cross Abstract: Technologies like large language models make it easier to convert cultural material into analyzable variables, while LLM-driven agentic systems extend
Chao Kong / South China Morning Post: Leading Chinese mathematicians launch an alliance, including eight orgs and aiming for 1,000+ scientists, to focus on developing specialized AI models for math —
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
Robert Hart / The Verge: Meta says it plans to power its Muse AI agent with Wonder, starting with subscribers, and will develop specialized models it “can bring to everyone using Muse” — Meta says the
arXiv:2610.13485v1 Announce Type: new Abstract: Agentic orchestration delegates tasks to sub-agents with independent contexts, providing a key path to extending the effective execution horizon of larg
arXiv:2610.13395v1 Announce Type: cross Abstract: Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to ge
Cheeky Pint: Q&A with Mark Zuckerberg and Alexandr Wang on the Muse app, Muse Wonder, the risks of committing $100B+ to AI, rebooting Meta's AI team, agentic commerce, more — As Meta scales its AI inf
arXiv:2610.13399v1 Announce Type: new Abstract: Long-term personalized tutoring requires language models to translate a learner's evolving history into appropriate instructional support. Existing LLM-
arXiv:2610.13166v1 Announce Type: new Abstract: Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool
arXiv:2610.13356v1 Announce Type: new Abstract: Coding agents are increasingly deployed for end-to-end software engineering tasks, where a readily available oracle evaluator that defines the success c
arXiv:2610.13626v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about
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:2610.13098v1 Announce Type: new Abstract: Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous su
Financial institutions are adopting artificial intelligence faster than many compliance teams can establish the controls needed to oversee it. That gap is raising new questions about AI-powered compli
arXiv:2610.13788v1 Announce Type: new Abstract: LiDAR-inertial odometry (LIO) is widely used for real-time localization and mapping, but its reliability can degrade substantially in subterranean envir
arXiv:2607.09996v2 Announce Type: replace Abstract: Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler
arXiv:2504.06185v3 Announce Type: replace-cross Abstract: Chronic wounds affect a large population, particularly the elderly and diabetic patients, who often exhibit limited mobility and co-existing h
A new work suggesting that division of labor among self-improving AI agents can help them avoid reinforcing their own errors. I found this work interesting from a metascience perspective. Science is a
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
Professional services firms are rethinking how they deliver client value as artificial intelligence takes on more routine work, shifting attention toward human judgment, trusted outcomes and new opera
Excited to be co-hosting our AIE NYC side event alongside @sfcompute! Looking forward to seeing everyone there. Capacity is limited and spots are filling up fast - RSVP below. @sfcompute and @jumptrad
good framing from @ch3nweiii - a lot of agent steps are yes/no calls, not generation Jev answers those as typed questions with calibrated probabilities, so the frontier model sticks to the hard work w
Reasoning From Scratch: Reinforcement Learning with Verifiable Rewards (RLVR) round 2. Covering clipped policy ratios, KL loss term, format rewards, and other GRPO tips & tricks. 00:00 Introduction an
Hey everyone! 👋 After months of building, we’re finally opening the first spots for **Many Agents**, a new product from Dome. The idea is simple: **What if you could create your own team of AI agents
I shipped a new feature for my blog today: the Newsletters page, which offers an index of all of the newsletters I've sent out, both my free weekly Substack and my monthly sponsors-only updates. I bui
arXiv:2610.11613v1 Announce Type: new Abstract: An agent can complete a task without improving how it works. Turning task experience into reusable capability requires connecting the changed component
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-
Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive su
Banger paper from Meta Superintelligence Labs on self-improving agents. (bookmark it) It's hard to know exactly what drives self-improvement, since so many variables are at play (notes, skills, tool c
arXiv:2503.06140v3 Announce Type: replace Abstract: Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated
arXiv:2610.11065v1 Announce Type: new Abstract: Automating city-scale wireless deployment remains challenging under complex urban propagation and network-wide interference. We introduce extbf{CityDepl
arXiv:2610.10809v1 Announce Type: new Abstract: Instance-specific rubrics are common in AI benchmarks where reliable evaluation requires specific expert knowledge. This approach is difficult to scale,
arXiv:2610.11899v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-au
arXiv:2610.11467v1 Announce Type: cross Abstract: We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Internet traces when privileged telem
arXiv:2610.12363v1 Announce Type: new Abstract: Intelligent grading and automated scoring technologies constitute critical infrastructure for smart education. However, existing document parsing and ha
arXiv:2610.10633v1 Announce Type: cross Abstract: Screening in systematic reviews (SRs) is manual and time-consuming. Prior work has explored large language models (LLMs) for automating this step, but
arXiv:2610.10854v1 Announce Type: new Abstract: Knowledge distillation is an established technique for improving the capabilities of small, efficient student models by training them with the represent
arXiv:2610.11599v1 Announce Type: cross Abstract: Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs). The reliability of this scree
arXiv:2607.16204v2 Announce Type: replace Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixe
arXiv:2610.11959v1 Announce Type: new Abstract: Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the
arXiv:2602.00811v2 Announce Type: replace Abstract: Current Multimodal Affective Computing (MAC) systems heavily rely on the completeness of multiple modalities to accurately understand human's affect
arXiv:2610.11605v1 Announce Type: cross Abstract: We introduce NanoProof, to our knowledge the first factorized execution-guided theorem prover in Lean 4 whose training data, extraction tooling, train
arXiv:2512.16545v3 Announce Type: replace-cross Abstract: Cu NPs have a broad applicability, yet their synthesis is sensitive to subtle changes in reaction parameters. This sensitivity, combined with
Everyone is very concerned about being respectable, so I’m going to be the goofball who raises worst-case possibilities. I think there is a 1% chance we live in Minicrypt, and a 15% chance we function
ik ik 'another harness D:'. so... i spent the last 6 months of my life building and ironing out every single detail and bug through almost every route with extensive testing across 3 machines, daily,
arXiv:2610.12233v1 Announce Type: cross Abstract: Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to pra
arXiv:2610.11593v1 Announce Type: cross Abstract: Coding agents produce large, tangled patches that mix multiple development purposes, making the code hard to review and maintain. Commit untangling of
arXiv:2610.11371v1 Announce Type: new Abstract: Contemporary decoder-only large language models (LLMs) have demonstrated strong capabilities across a wide range of domains. However, existing pretraini
arXiv:2610.10560v1 Announce Type: cross Abstract: AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting. Their
arXiv:2610.10768v1 Announce Type: cross Abstract: The global challenge of climate change has driven significant steps to reduce CO2 emissions, guided by international agreements like the Paris Agreeme
arXiv:2610.12272v1 Announce Type: new Abstract: This paper investigates the feasibility of deploying quadruped walking robots for the automation of work in roof environments. While quadrupeds have dem
arXiv:2610.11508v1 Announce Type: cross Abstract: Despite recent advances in Vision-Language-Action models (VLAs) for robotic manipulation, their performance remains sensitive to changes in camera con
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:2610.11291v1 Announce Type: new Abstract: On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models. In this work, we ask a critical re