Search: “agents”

🧵 Slime: The Most Elegant & Comfortable RL Training Framework Ever A deep dive into why Slime redefines LLM RL training with clean architecture & production-grade engineering ✨ Insights from Zhihu con

arXiv:2605.07127v1 Announce Type: cross Abstract: Modern large language models (LLMs) can find a needle in a haystack (locating a single relevant fact buried among hundreds of thousands of irrelevant

arXiv:2512.03454v4 Announce Type: replace-cross Abstract: Interpreting natural-language commands to localize target objects is critical for autonomous driving (AD). Existing visual grounding (VG) meth

“we gonna yolo our way into running the biggest conf in town.” and somehow… we actually did it with @aiDotEngineer singapore a year ago, @agrimsingh @unprofeshme and i joked about the idea of running

Your AI Use Is Breaking My Brain Excellent, angry piece by Jason Koebler on how AI writing online is becoming impossible to avoid, filtering it is mentally exhausting and it's even starting to distort

Anna Tong / Forbes: A look at Janitor AI, a romantic fantasy roleplay chatbot site run by three men that claims 2.5M DAUs and 15M total users, with 70% to 80% identifying as women — Despite its name,

100% agree on the Context Hub. Developers constantly tweak their approaches to manage context in their prompts with each new model and tool suite release. I would even say that the core problem we fac

ERNIE 5.1 is here 🚀 ERNIE 5.1 significantly reduces pretraining cost while compressing total parameters to ~1/3 and activated parameters to ~1/2 — using only ~6% of the pretraining cost compared to mo

I recently installed Hermes after raw-dogging Claude Code for a year or so. Have tried it at work, didn't see the need to implement it personally. Always had the usual fears about 'privacy' and what n

Grammar-constrained decoding modifies language model generation by applying grammar constraints at each step to block structurally invalid tokens , ensuring syntactically correct Bash command generati

Remember that MIT study that showed that the ROI for generative AI wasn’t really there for most businesses? Or any of the six or seven studies from other teams that followed, showing basically the sam

Thank you to @robertwiblin for inviting me on the @80000Hours podcast to discuss the research progress we’re making at @LawZero_ to create safe-by-design AI systems. Our current approach, Scientist AI

Apple CEO Tim Cook acknowledged in Q2 2026 earnings that high-demand Mac mini and Mac Studio configurations are severely constrained and may take several months to reach supply-demand balance. Apple h

arXiv:2605.04083v1 Announce Type: new Abstract: Much of the focus in RL today is on evaluation design: building meaningful evals that serve simultaneously as benchmarks and as well-defined reward sign

Congrats on the launch! Filesystems are all you need (?) There wasn't a huge demand for 'managed RAG' services in 2023, but it's possible the infra and market was just not mature enough. Maybe filesys

arXiv:2605.03900v1 Announce Type: new Abstract: Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and

Hacker News → LLM Artifact I built the most personalized HN feed. It only tracks topics I do research around based on memory and LLM wiki. No point in storing bookmarks. With a few automations, rules,

I really enjoyed chatting with @mattturck, was a great discussion. Deeply thoughtful conversation with @zicokolter, board member at @OpenAI and head of the machine learning department at @CarnegieMell

arXiv:2605.04355v1 Announce Type: new Abstract: Autonomous driving systems rely heavily on robust sensor fusion to perceive complex envi- ronments. Traditional setups using RGB cameras and LiDAR often

arXiv:2602.04129v2 Announce Type: replace Abstract: Heterogeneous multi-robot systems are increasingly used in long-horizon missions requiring coordinated planning across diverse capabilities. However

arXiv:2512.23864v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown remarkable generalization by mapping web-scale knowledge to robotic control, yet they remain bl

arXiv:2605.03216v1 Announce Type: cross Abstract: Strategy-proofness is a fundamental desideratum in mechanism design, ensuring truthful reporting and robust participation. Stability is another centra

arXiv:2605.05163v1 Announce Type: new Abstract: Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on

arXiv:2605.04496v1 Announce Type: new Abstract: Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can

Searching for the right context in a sea of information is such a timeless problem in our field. I'm excited to talk about some of the approaches we've learned and benefited from at Thrive next week a

arXiv:2605.04877v1 Announce Type: cross Abstract: Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict. Crucia

We already had gemini-3.1-flash-lite-preview back on March 3rd, not clear if this new gemini-3.1-flash-lite is different other than no longer being marked as a 'preview'. Pricing appears to be the sam

We've teamed up with @cerebras to offer free Windsurf plans for SWE-1.6 Fast Mode at up to 1000 tok/s! Fast Mode is built on Cerebras inference, enabling superior speed for planning and development wi

arXiv:2605.02669v1 Announce Type: new Abstract: Drug-induced liver injury (DILI) remains a leading cause of late-stage clinical trial attrition. However, existing computational predictors primarily re

arXiv:2605.04045v1 Announce Type: new Abstract: Audio-Visual Intelligence (AVI) has emerged as a central frontier in artificial intelligence, bridging auditory and visual modalities to enable machines

arXiv:2605.02454v1 Announce Type: cross Abstract: Software engineering increasingly involves making high-stakes decisions under uncertainty, using signals from code, field data, and socio-technical pr

arXiv:2605.01338v1 Announce Type: new Abstract: System-level diagrams encode the architectural blueprint of chip design, specifying module functions, dataflows, and interface protocols. However, non-s

arXiv:2601.07885v2 Announce Type: replace-cross Abstract: Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs)

arXiv:2605.02832v1 Announce Type: new Abstract: Deciding how to distribute work between humans and AI systems is a central challenge in organisational design. Most approaches treat this as a binary ch

Simon Willison's live blog covers Anthropic's Code w/ Claude 2026 event, documenting the morning keynote sessions with real-time updates. The event featured announcements including updates to Claude m

arXiv:2605.02087v1 Announce Type: new Abstract: Some frontier AI developers aim to align language models to a Model Spec or Constitution that describes the intended model behavior. However, standard a

arXiv:2412.14737v2 Announce Type: replace Abstract: The rise of large language models (LLMs) and their tight integration into our daily life make it essential to dedicate efforts towards their trustwo

OpenAI is fast-tracking development of its first AI-focused smartphone with mass production targeted for early 2027 , marking the company's entry into consumer hardware . The device, positioned as an

arXiv:2605.03129v1 Announce Type: cross Abstract: Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style persona

@PPLXfinance @PPLXDevs On FinSearchComp T1, Finance Search delivered the highest accuracy for live financial data and the lowest cost per correct answer in the cohort. Every result includes citations,

Two weeks after release, Hy3 preview is #1 on @OpenRouter's weekly leaderboard with 3.66T tokens processed, up 298% week-over-week. #1 in overall usage, tool calls, and coding. 15.4% market share acro

arXiv:2605.01278v1 Announce Type: new Abstract: In this work, we present Valley3, an omni multimodal large language model (MLLM) developed for diverse global e-commerce tasks, with unified understandi

arXiv:2603.04601v2 Announce Type: replace-cross Abstract: Code generation has emerged as one of AI's highest-impact use cases, yet existing benchmarks measure isolated tasks rather than the complete '

We built a simple app that's also probably the best PDF -> text phone app there. Take a picture of any document: a filled out form, identification, a statement, an essay - and we'll convert it into we

we're continuing to see clear examples where a model's harness is a major determinant of overall performance. with the same model, running on same task, it's easy to observe very different scores depe

arXiv:2605.00909v1 Announce Type: cross Abstract: The time-consuming formation process critically impacts the longevity of sodium-ion coin cells and End Of Life (EOL) performance. This study aims to o