Search: “engineering”

arXiv:2607.21412v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially i

arXiv:2607.21522v1 Announce Type: cross Abstract: Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging. Traditional computer graph

arXiv:2607.20468v1 Announce Type: new Abstract: AI agents are increasingly used to automate research and development tasks, yet existing benchmarks typically evaluate them on prescribed workflows or n

arXiv:2607.20427v1 Announce Type: cross Abstract: Mixture-of-Experts architectures have revolutionized scaling, yet the underlying logic of their routing remains a black box. In this paper, we uncover

arXiv:2601.21284v2 Announce Type: replace-cross Abstract: Diffusion models have emerged as powerful generative tools for modeling complex data distributions, yet their purely data-driven nature limits

arXiv:2602.10226v2 Announce Type: replace-cross Abstract: Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyper

arXiv:2607.20911v1 Announce Type: new Abstract: We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring pro

arXiv:2607.09988v3 Announce Type: replace-cross Abstract: Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse cont

arXiv:2507.08716v4 Announce Type: replace Abstract: Large-scale, precisely synchronized multi-modal datasets are critical for data-driven sixth-generation (6G) wireless research, yet real-world collec

The math behind reinforcement learning (RL) post-training for large language models (LLMs) is notoriously unforgiving. As frontier AI labs push the boundaries of reasoning and coding models using RL p

arXiv:2607.18722v2 Announce Type: replace-cross Abstract: Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byp

arXiv:2607.19992v1 Announce Type: cross Abstract: tiny_schiller closes the small-language-model prototyping, fine-tuning, education, and research gap for German literary text, providing a single-file,

arXiv:2607.19595v1 Announce Type: cross Abstract: Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream

Hey HN, Henry & Roman here from Cactus. A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-t

Progressive disclosure in agents doesn't scale. And its benefits seems agent harness dependent. (bookmark this one) Finally there is a proper study on using agent skills and the effect of progressive

We dropped some new LlamaDrip 🧢 Fear of Docs LlamaParse The team flew into SF for a week onsite. 🌉 2x'd in size since we last did this — first time this many of us have been in the same room. The reca

I thought this was a very good post by @c_valenzuelab and really highlights how transformative video models already are for the businesses that are using them. I think video models are one of the most

Highly recommended. I've often claimed there's huge alpha in building agent harnesses. Turns out harnesses are compositional generalizers. The RLM harness is an instance of this. This could lead to in

People are wasting their AI subscriptions. They don’t realize how powerful AI can be in achieving their own goals. They’re asking AI to reply to emails with zero goals in mind and nothing laddering up

arXiv:2607.13221v1 Announce Type: cross Abstract: Real-time N-1 contingency screening in an energy management system trades assurance against cost: verifying every credible outage with full power flow

arXiv:2607.13071v1 Announce Type: cross Abstract: Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth. This paper docume

arXiv:2607.14004v1 Announce Type: new Abstract: Most reported gains from agent-optimization methods are one-shot: an agent is optimized against a fixed benchmark and the resulting improvement is repor

arXiv:2607.13303v1 Announce Type: cross Abstract: Formal contracts are essential for software testing and verification, yet writing them remains labor-intensive and error-prone. LLMs offer a promising

arXiv:2607.13285v1 Announce Type: new Abstract: The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes t

arXiv:2607.13220v1 Announce Type: new Abstract: Most AI-for-science systems focus on scaling a single reasoning process through better models, larger context windows, long-horizon agentic execution, o

arXiv:2607.13091v1 Announce Type: cross Abstract: LLM-based coding agents repeat the same classes of mistakes across sessions because they lack a mechanism to retain corrections from human review feed

arXiv:2607.11673v2 Announce Type: replace Abstract: We present ABot-3DWorld 0, a universal multimodal 3D world model that turns text, image, and video inputs into high-fidelity, explorable 3D worlds.

arXiv:2607.12634v1 Announce Type: new Abstract: This paper proposes a theoretical framework for understanding intelligence as a process of atomic compression and compositional reuse. We argue that cog

arXiv:2607.11914v1 Announce Type: cross Abstract: A central goal of current Spiking Neural Network (SNN) research is to improve their accuracy toward becoming low-power alternatives to Artificial Neur

Creatio Inc. today introduced what it calls a major update to its customer relationship management and workflow platform that enables business users and information technology teams to build, deploy a

Deploying the Gemini Enterprise app across an organization marks a transformative leap forward in workforce productivity, providing employees with an amazing, high-performance suite of agentic AI tool

Interrupt is hitting the road this fall: 📍 NYC- September 24 📍 London- October 13 Info + RSVP: https://interrupt.langchain.com/ At Interrupt, @RCUmmadisetti and @kordelfrance from @Toyota's enterprise

arXiv:2607.11327v2 Announce Type: replace-cross Abstract: Model editing keeps large language models (LLMs) up to date without retraining, but temporal facts expose a limitation of the prevailing locat

arXiv:2607.12398v1 Announce Type: new Abstract: Freehand 3-D ultrasound (US) imaging has attracted increasing attention owing to its intuitive volumetric visualization, ease of use, and low cost. Howe

We're part of the Amazon Web Services (AWS) AI Builder Lab in New York on Friday, July 24 - a Clash of Agents competition with OpenAI, LangChain, HiddenLayer, Protopia AI, Fiddler AI, and Coder. One d

Agreed with this. people underestimate the importance of good abstractions and maintainability. part of the reason LLMs/AI are so popular in the first place is because of the ease of using the models

The emergence of artificial intelligence has raised expectations for enterprise search, but the results do not always inspire confidence. Users may encounter fragmented or irrelevant search results or

Exactly one year ago was the craziest 72 hours I’d experience in Silicon Valley. I was thrust into a situation where many members of the Windsurf team had moved on to Google, recruiters were reaching

At Observe 2026, Jason Lopatecki and Aparna Dhinakaran described the shift from human-operated agent development to systematic agent improvement—and what builders should change in their stacks first.

For years, we’ve built with a clear priority: putting the practical needs of the enterprise first. Long before generative AI dominated the headlines, we were focused on building the global infrastruct

Retail Finance teams are increasingly deploying agentic AI to safeguard omni‑channel margins. These systems automatically monitor sales performance, forecast demand, and adjust pricing or inventory co

Just a reminder that deepseek v3 came out 18 months ago and was considered revolutionary at the time but is basically unusable today There was a fierce debate at the time about vibe coding and the arg

dam bois we eating good this week ngl, The velocity of the open_weight ecosystem right now is hitting a point where proprietary, closed-source APIs are losing their leverage on compute intelligence. W

Oracle Corp. today announced a new artificial intelligence-native experience for its Fusion Applications within Oracle AI Agent Studio, allowing developers, customers and partners to build agents toge

The shared language of a software project is not English or Python but it is the common understanding of what its concepts mean, where the boundaries are, which invariants matter, who owns what, and w

// An Anatomy of CLI Coding Agent Trajectories // (bookmark it) When your coding agent fails a task, when did the run actually go wrong? Most reliability studies use the final label to answer this. Th