Knowledge catalogue
I’ve been building ClawLite, an open-source personal AI assistant that talks to you through Telegram and defaults to Ollama (local models). What it does: Multi-agent research with actual cross-source
arXiv:2607.24762v1 Announce Type: new Abstract: Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as mat
arXiv:2606.18902v2 Announce Type: replace Abstract: Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do
The problem: agent workflows alternate between GPU-heavy reasoning and GPU-idle waiting on tools. Run hundreds concurrently and their KV caches fight for memory. Engines evict on a dumb LRU policy, ev
The first autonomous agent cyberattack is an unprecedented event that deserves unprecedented transparency. Today we're sharing everything we can: a full technical timeline, an interactive replay, and
arXiv:2505.12650v2 Announce Type: replace-cross Abstract: Reconstructing atomistic crystal structures from a single noisy STEM projection is an ill-posed inverse problem: multiple lattices can explain
arXiv:2607.24313v1 Announce Type: cross Abstract: Marine life monitoring is limited by strict energy constraints, poor underwater connectivity, and the high cost of transmitting raw multimodal data fr
arXiv:2607.23006v1 Announce Type: cross Abstract: Scientific question answering requires a retrieval system to solve two distinct problems: identifying which papers are relevant and locating the suppo
arXiv:2607.22241v1 Announce Type: new Abstract: Recent advances in video diffusion models have spurred interest in human-object interaction (HOI) video generation, which demands fine-grained control o
Someone in the comments of my 27B post-train bakeoff asked for the 35B version, so I ran it. Same setup as last time: fresh Coder workspaces on my k8s cluster, each driving my own agent (Hermes) headl
@Kimi_Moonshot K3 on Together AI is built for long-running agent workflows: → 2.8T parameters and a 1M context window → Native vision for screenshot-guided coding → Repository navigation and terminal
New York Times: Microsoft introduces MAI-Cyber-1-Flash, an AI model trained for cybersecurity, and launches Perception, an agentic security system to patch vulnerabilities — As some executives fret ov
I got tired of my Ollama server sitting idle between chat experiments, so I pointed it at my Navidrome library and made it run a radio station. The DJ is an agent, not a shuffler. Each turn it gets to
arXiv:2607.20827v1 Announce Type: new Abstract: LLM agents choose tools and arguments from context that mixes user requests, tool outputs, retrieved records, memory, and untrusted text. Evidence can b
arXiv:2607.21419v1 Announce Type: new Abstract: In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting
arXiv:2607.21518v1 Announce Type: new Abstract: Even a current high-capability LLM can appear safer when shown a dangerous objective directly than when other agents transform and relay its direction.
Advanced Micro Devices Inc. is pushing harder than ever to grab even more market share from Nvidia Corp. in the artificial intelligence chip industry. At its Advancing AI 2026 event today in San Franc
arXiv:2510.05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a singl
Sydney Runkle inquires whether anyone is exploring graph engineering that aligns with Claude’s dynamic workflows, specifically whether an agent could author its own state machine. The suggested approa
Today we’re releasing Poolside Laguna S 2.1 It is a 118B-total, 8B-active open-weight model built for agentic coding and long-horizon work, with context up to 1M tokens https://poolside.ai/blog/introd
We talked about Claude Code, Claude Tag, Fable, coding agent security, evals, tool design, and how Anthropic use these tools themselves Claude Tag (Claude Code via Slack) is already landing 65% of the
In this post, we show how Amazon Quick can serve as the business-user front door for specialized agent workflows. We use the NVIDIA NeMo Relay to build a supply-chain risk example that helps a planner
arXiv:2607.13049v1 Announce Type: new Abstract: Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still de
Marco Chiappetta / Forbes: Cadence unveils AuraStack AI Super Agent, an AI platform for PCB and advanced chip packaging design, with Nvidia, TSMC, and Schneider Electric among early users — As systems
arXiv:2603.28583v2 Announce Type: replace-cross Abstract: Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structure
arXiv:2607.11910v1 Announce Type: cross Abstract: Optimizing composite stacking sequences to match continuous targets (e.g., Lamination or Buckling Parameters) with discrete manufacturing constraints
Absolutely fascinating work by @SakanaAILabs reproducing @kenneth0stanley Picbreeder in a non-interactive, VLM-agentic way. I've had years to reflect on Kenneth Stanley's ideas as originally communica
arXiv:2607.07859v1 Announce Type: new Abstract: Reinforcement learning (RL) research has increasingly shifted focus towards alignment, ensuring agents learn behaviors adhering to human values. While h
arXiv:2607.06957v1 Announce Type: cross Abstract: Realistic and diverse traffic simulation is essential to autonomous driving development. Yet prevailing benchmarks predominantly reward realism, and r
arXiv:2607.07403v1 Announce Type: cross Abstract: Vision Language Models (VLMs) and Vision Language Action (VLA) models have shown promise in robotic control. Yet, they face significant challenges reg
Notes on GPT-5.6, which includes some interesting new additions to the API (programmatic tool calling and multi-agent in particular) - plus 18 pelicans for the 6 reasoning levels and 3 new models: htt
Axios: OpenAI broadly releases GPT-5.6, and launches ChatGPT Work, an AI agent that can gather context across apps and files to create documents, on Mac and Windows — - Sol is the most powerful versio
Nice stats on usage of open models across OpenCode. GLM-5.2 is still underrated, but one of the models that has really surprised me on agentic tasks is deepseek-v4-flash. Extremely cheap and effective
arXiv:2607.05805v1 Announce Type: new Abstract: Dilution refrigerators are the enabling infrastructure of superconducting quantum computers, yet their fault diagnosis is still dominated by threshold a
arXiv:2607.04574v1 Announce Type: cross Abstract: For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on.
arXiv:2607.04331v1 Announce Type: cross Abstract: Evaluating autonomous driving systems in closed-loop settings requires realistic and interactive simulation, yet existing simulators largely rely on l
arXiv:2408.13378v5 Announce Type: replace Abstract: Workflows in drug-target interaction (DTI) assessment require integrating heterogeneous data from predictive models, curated resources, and observat
arXiv:2607.05134v1 Announce Type: cross Abstract: We present PDEFlow, an autonomous agentic framework that turns user-level ODE and PDE descriptions into solver-backed neural-operator pipelines. The w
arXiv:2607.04470v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement
Sakana AI (@SakanaAILabs) is now a model vendor on Merge Gateway, and Fugu Ultra is live through them. It's a multi-agent orchestration model that routes across frontier models behind one API. You get
arXiv:2607.03333v1 Announce Type: cross Abstract: LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: th
The release of Fable 5 just points to the importance of agent orchestration. You really don't need Fable 5 for most tasks. You can plan with Opus 4.8/Fable 5, execute with GPT-5.5, and design with GLM
128 GB of memory is nice, but you can get started with local agentic AI workflows with much less. By connecting gemma 4 in @lmstudio to MATLAB MCP Server, you can run a local AI model that uses MATLAB
Jason Hiner / The Deep View: Q&A with Doug Brooks, senior product manager of Apple silicon, about Mac minis becoming preferred AI agent machines, future of on-device AI, and more — W — alk into any of
arXiv:2607.01935v1 Announce Type: new Abstract: Long term memory lets LLM agents act as persistent assistants, but user facts change. A useful memory system must know what is true now, what used to be
arXiv:2607.02141v1 Announce Type: new Abstract: Most LP-from-text benchmarks are static datasets of word problems written and labeled by hand. Once such a dataset is released, its size is fixed, its d
arXiv:2607.01366v1 Announce Type: new Abstract: Federated learning (FL) research often depends on many small but consequential algorithmic choices: optimizer variants, server aggregation rules, local
arXiv:2607.02387v1 Announce Type: cross Abstract: NASA and its data centers hold thousands of geoscience datasets and tools like Worldview, Giovanni, the Science Discovery Engine, and Harmony. Finding
arXiv:2607.02245v1 Announce Type: new Abstract: Mental health disorders affect nearly one billion people globally, yet 75% of individuals in low- and middle-income countries receive no treatment due t
arXiv:2607.01767v1 Announce Type: new Abstract: As agent planning moves from short tool chains toward persistent workflows with thousands or tens of thousands of steps, failures will occur inside larg
arXiv:2607.02370v1 Announce Type: cross Abstract: Compiler missed optimizations refer to cases in which compilers failed to optimize certain code. It takes many compiler developers' efforts to impleme
big week at langchain, with a lot of launches: 1/ OpenWiki - auto generate a wiki of a github repo 2/ two different voice agent tutorials 3/ Harbor integration and tutorial for long running, stateful
i finally tried hermes agent and the hype is real btw. @NousResearch cooked. been onboarding my young relatives who can't afford Claude, showing them how to use $1-5 of tokens to bootstrap hermes and
Your coding agent bill doubled and nobody can tell you why. Here's the actual reason: Claude Code, Cursor, and Copilot all log activity in different formats. The second your team uses more than one (t
Michael Nuñez / VentureBeat: Z.ai launches ZCode, an “Agentic Development Environment” optimized for its new GLM-5.2 model; Z.ai's GLM Coding Plan costs from 16.20 to 144 per month — The move marks th
“Agentic kernel optimization is the future of on-device inference” @xenovacom used Fable 5 to write kernels that pushed Gemma 4 to a massive 255 tok/s on WebGPU with M4. He shared the demo, so you can
arXiv:2606.30949v1 Announce Type: new Abstract: High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challen
arXiv:2606.32007v1 Announce Type: new Abstract: We study agentic code generation in Dafny, where a model must generate both executable code and the proof artifacts for verification. We present AxDafny
do you know what you pay for in agentic workloads? cached tokens! session with 50+ tool calls -> prompt is billed 50 times all providers give 1/5 cached discount for GLM-5.2 we at @FireworksAI_HQ drop
arXiv:2606.31650v1 Announce Type: cross Abstract: Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Existing cont