Is ternary (1.58-bit) LLMs making a come back?
I'm just thinking, ever since microsoft announced bitnet, this sub (and myself) has been hoping for massive ternary models. In the last month alone, prismML dropped 27B ternary (though I've read commu
Knowledge catalogue
I'm just thinking, ever since microsoft announced bitnet, this sub (and myself) has been hoping for massive ternary models. In the last month alone, prismML dropped 27B ternary (though I've read commu
o3-mini (very obsolete) in an agentic loop made good exam questions: 'In one of the largest field studies of AI-generated questions to date, we found that this approach achieves psychometric propertie
totally agree! here's how we architected deepagents to enable this deepagents runs connected to a 'backend'. this backend needs to expose filesystem like operations, but it does not have to be a files
After using Grok Bot nonstop for the past week I'm going to say it: it's the best AI agent out there right now Dead simple and just works It eliminates the 10,000 decisions, configs, and fixes that sc
gave a talk 'owning your intelligence' - ty @sequoia @sonyatweetybird for having me talked about harnesses and evals and the role they play in owning your intelligence TLDR: > agents = model + harness
Grok 4.6 is my daily driver now. This is why: When I’m using interactive agents in a CLI/terminal (or even Slack), what matters most to me is speed & token throughput. Intelligence and differences in
@hwchase17 @LangChain I built an open-source CLI that scaffolds, runs, and deploys production LangChain agents — frontend and backend in one command. Every agent project starts the same way: wire up a
It makes sense to optimize model routing at the harness layer instead of the gateway layer if you want to hillclimb on accuracy/cost for any e2e task. Every task is solved by a combination of a model
New work from Google DeepMind and collaborators. Agentic algorithm discovery keeps getting demonstrated on problems with fast rewards. Microarchitecture has vast search spaces, strict hardware budgets
Alix Coutures / The Information: Sources: Mercor and other firms gathering data for AI labs are driving demand to buy or license internal datasets from startups shutting down or being acquired — Eight
arXiv:2608.13472v1 Announce Type: cross Abstract: Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition.
arXiv:2603.08322v2 Announce Type: replace Abstract: We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with
arXiv:2608.12866v1 Announce Type: new Abstract: Reliable relative pose estimation between autonomous underwater vehicles (AUVs) is critical for cooperative ocean exploration, sampling, and multi-robot
arXiv:2608.12841v1 Announce Type: cross Abstract: We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier exper
arXiv:2608.13417v1 Announce Type: new Abstract: Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation. To understa
arXiv:2608.12977v1 Announce Type: cross Abstract: The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as
arXiv:2608.12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities,
arXiv:2608.13046v1 Announce Type: new Abstract: Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-age
arXiv:2608.12854v1 Announce Type: cross Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typical
Learn how to combine OpenAI-compatible endpoints on Amazon SageMaker AI with Amazon Bedrock AgentCore runtime to build a multi-agent workflow where each specialized agent uses the model best suited to
arXiv:2608.12761v1 Announce Type: new Abstract: Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct acti
arXiv:2608.12921v1 Announce Type: cross Abstract: The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology
arXiv:2603.27803v2 Announce Type: replace Abstract: We provide a distributed online algorithm for multi-agent submodular maximization under communication delays. We are motivated by the future distrib
arXiv:2608.13096v1 Announce Type: new Abstract: Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, cont
arXiv:2505.04997v3 Announce Type: replace Abstract: Computational fluid dynamics (CFD) has been the main workhorse of computational physics, yet its steep learning curve and fragmented, multi-stage wo
arXiv:2608.13147v1 Announce Type: new Abstract: Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera streams.
Have been thinking about building a custom harness because nothing out there quite meets my needs for scaling a fully hybrid human + AI company, especially when it comes to compounding learning loops.
See how four GitHub agent apps can help you scope, secure, roll out, and ship a feature across the SDLC–all without leaving GitHub. The post How to bring your software delivery workflow into GitHub wi
A background comment about pizza exposed a failure that Uber’s offline evaluations had missed. The incident helped reveal what production AI agent evaluation actually requires: automatic tracing, livi
arXiv:2608.12358v1 Announce Type: cross Abstract: Product and engineering teams building role-bearing AI agents face an evaluation gap: an agent can produce accurate, safe, and fluent content while st
Introducing GLM-5.3: Built to Code. Ready for Cyber Defense. - Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model - A major leap in cybersecurity, setting
arXiv:2608.12880v1 Announce Type: cross Abstract: Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution
arXiv:2601.10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high infe
arXiv:2608.12674v1 Announce Type: new Abstract: Maintaining price consistency and executing an Every Day Low Price strategy is critical for global retailers. However, with catalogs spanning millions o
Murtaza Khomusi posted a tweet (12:58 AM UTC, Aug 14 2026) announcing that he had never before added a “kitschy discount sticker” beside a promotional tier on the LlamaIndex pricing page. The tweet in
Max-level intelligence, one API call away. Qwen3.8-2.4T-A95B is now live on DeepInfra, ready for your creative builds. 🥳 Take a deep dive on DeepInfra! @DeepInfra New on DeepInfra: Qwen3.8-2.4T-A95B 🚀
arXiv:2608.12771v1 Announce Type: cross Abstract: The extent to which large language models for code rely on memorization over genuine understanding remains highly debated. While current literature fr
arXiv:2608.13448v1 Announce Type: new Abstract: Social robots are expected to operate across diverse environments, where similar arrangements can imply different socially appropriate actions, e.g., st
arXiv:2608.12428v1 Announce Type: new Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. Howeve
arXiv:2608.13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty
notes on 'How to do data' from th Zai team that others should steal as they build their own environments - 'Research agents collect task patterns from real work and turn them into runnable long-horizo
arXiv:2608.13558v1 Announce Type: new Abstract: Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and cod
arXiv:2608.13510v1 Announce Type: cross Abstract: Machine learning procedures are commonly evaluated in terms of predictive accuracy and computational efficiency. However, their achievable performance
arXiv:2603.15605v2 Announce Type: replace Abstract: Autonomous exploration in unknown environments typically relies on onboard state estimation for localisation and mapping. Existing exploration metho
arXiv:2608.12325v1 Announce Type: new Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent ad
arXiv:2602.20017v2 Announce Type: replace Abstract: Real-world tables often contain schema inconsistencies, heterogeneous value formats, and implicit relational structures that degrade table reasoning
arXiv:2608.13102v1 Announce Type: new Abstract: Dense metric depth prediction from cameras and millimeter-wave radar offers a cost-effective sensing solution for autonomous systems. However, radar mea
arXiv:2608.13334v1 Announce Type: new Abstract: LLM-based agents increasingly rely on external memory to support long-horizon reasoning and interaction. However, the main bottleneck is not simply stor
arXiv:2608.12707v1 Announce Type: new Abstract: Hierarchical open-vocabulary object navigation (OVON) requires agents to follow free-form instructions that may specify targets through scene-, room-, r
arXiv:2608.13120v1 Announce Type: new Abstract: Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they migh
arXiv:2608.12610v1 Announce Type: new Abstract: There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's
arXiv:2608.13272v1 Announce Type: new Abstract: A small number of firms based in two states produce the most capable frontier AI models. The governments of those states have shown both the legal power
arXiv:2608.12440v1 Announce Type: cross Abstract: This paper reports a single, fully instrumented case study of a large-scale architectural refactoring by an AI coding agent under a specification-firs
arXiv:2608.12751v1 Announce Type: cross Abstract: Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making
arXiv:2608.13031v1 Announce Type: cross Abstract: Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents, viola
arXiv:2608.13060v1 Announce Type: new Abstract: Machine learning theory studies learning procedures through mathematical setups in which the data model, training protocol, oracle access, loss, metric,
arXiv:2608.12721v1 Announce Type: new Abstract: Complex video object segmentation requires robust target propagation under severe occlusion, disappearance and reappearance. Although SAM3 provides stro
Artificial intelligence agents are already running inside your enterprise workflows, whether you know it or not. International Data Corp. projects full agentic AI deployment across the enterprise by 2
arXiv:2505.05474v2 Announce Type: replace Abstract: 3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as imme
arXiv:2608.11211v1 Announce Type: new Abstract: Conway's 99-graph problem asks whether a strongly regular graph with parameters srg(99,14,1,2) exists. We report a systematic, fully reproducible attack