Knowledge catalogue
GitLab Act 2 There's a lot going on in this announcement from GitLab about the 'workforce reduction' and 'structural and strategic decisions' they are making with respect to the agentic era. They're '
arXiv:2510.11144v2 Announce Type: replace-cross Abstract: An agent facing a planning problem can use answers to how-to questions to reduce uncertainty and fill knowledge gaps, helping it solve both cu
The Harness is a Context Manager on Behalf of the Model What happens when the context window fills up and who decides? This decision is external to the model - The Harness designer must have some opin
One thing I love about LangChain is how the OSS pieces build on each other You can build robust workflows directly with LangGraph, our orchestration framework. We also use it as the foundation for Dee
It's only been two months, can't believe the growth and community we've built, together, around this! Thanks again everyone. Meet Hermes Agent, the open source agent that grows with you. Hermes Agent
arXiv:2604.23027v1 Announce Type: new Abstract: Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based re
arXiv:2604.24117v1 Announce Type: new Abstract: Efficient job-shop scheduling with transportation resources is critical for high-performance manufacturing. With the rise of 'decentralized factories',
arXiv:2604.24710v1 Announce Type: new Abstract: Objective. Clinical AI documentation systems require evaluation methodologies that are clinically valid, economically viable, and sensitive to iterative
arXiv:2601.17736v2 Announce Type: replace-cross Abstract: Interactivity is crucial for effective data visualizations. However, it is often challenging to implement interactions for existing static vis
arXiv:2601.03555v2 Announce Type: replace Abstract: Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning.
Agentic AI is flooding enterprise pipelines with possibility, but regulated industries are learning that the speed of deployment and the discipline of governance cannot be decoupled — and that AI proc
arXiv:2603.01168v2 Announce Type: replace-cross Abstract: Reliable decision-making in complex multi-agent systems requires calibrated predictions and interpretable uncertainty. We introduce SphUnc, a
Yann LeCun (AMI Labs Founder): 'The AI industry is completely LLM-pilled. Everybody is working on the same thing. They're all digging the same trench.' LeCun explains why no lab dares break from the p
haha My @NousResearch hermes-agent can make movies now using @browser_use skill. No API needed. No human intervention. No bottleneck. Just logged into my Higgsfield account and my hermes-agent goes to
arXiv:2604.17189v1 Announce Type: new Abstract: In this study, we propose a new sheepdog-inspired control method for a swarm of small unmanned aerial vehicles (UAVs), which predicts the swarm behavior
This post likely emphasizes the 'weakest link' principle in cybersecurity, illustrating how comprehensive security systems can be compromised through a single vulnerable component, whether that's outd
'I am envisioning a harmonious interplay of form and space, where each element finds its rightful place within the visual narrative. The pelican emerges as a central figure, its wings poised in dynami
arXiv:2604.13849v1 Announce Type: cross Abstract: The rapid proliferation of Model Context Protocol (MCP)-based agentic systems has introduced a new category of security threats that existing framewor
arXiv:2604.13381v1 Announce Type: cross Abstract: Conversational generative artificial intelligence agents (or genAI chatbots) could benefit youth mental health, yet young people's perspectives remain
Radio-frequency identification devices and software company Impinj Inc. today announced an upgrade of its R700 RAIN RFID reader with a more powerful processor and expanded memory to help enterprises b
arXiv:2604.12666v1 Announce Type: cross Abstract: Text-based web agents offer computational efficiency for autonomous web navigation, yet developing robust agents remains challenging due to the noisy
Traditional data centers only stored, retrieved and processed data. In the generative and agentic AI era, these facilities have evolved into AI token factories. With AI inference becoming their primar
arXiv:2604.09866v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have shown the promise to significantly accelerate the workflow by automating structural modeling and
Cursor has published a research post in collaboration with NVIDIA exploring multi-agent kernel systems, likely detailing how multiple AI agents can work together to handle complex coding or computatio
arXiv:2604.04334v2 Announce Type: replace-cross Abstract: Researchers and practitioners are increasingly considering reinforcement learning to optimize decisions in complex domains like robotics and h
arXiv:2603.28013v3 Announce Type: replace-cross Abstract: Multi-agent LLM systems are entering production -- processing documents, managing workflows, acting on behalf of users -- yet their resilience
LangChain has launched a new podcast focused on the theme of empowerment, as announced by Harrison Chase on X (formerly Twitter). The podcast likely features discussions around AI development, buildin
Harrison Chase, co-founder of LangChain, wrote a post in a similar style to a piece by Sarah Wooders, focusing on the concept of 'your harness, your memory' in the context of AI agents and memory syst
🚨 AI DOOM IS 50% @emostaque says there’s a coin flip chance AI goes very badly. One path looks like Star Trek. The other looks like a billion autonomous robots with bad firmware. And nobody can shut t
arXiv:2604.06373v1 Announce Type: cross Abstract: New generation of AI coding tools, including AI-powered IDEs equipped with agentic capabilities, can generate code within the context of the project.
arXiv:2604.07016v1 Announce Type: new Abstract: A key challenge in scaling up Reinforcement Learning is generalizing learned behaviour. Without the ability to carry forward acquired knowledge an agent
This Week in Replit. New Skills: SEO Auditor, BDR, Stock Analyst, Interviewer. SEO Auditor is blowing up. Amazing work, @samuel_spitz ! Accenture partnership is live. Consultants shipping working prot
arXiv:2604.07960v1 Announce Type: cross Abstract: Computer-Aided Design (CAD) is an expert-level task that relies on long-horizon reasoning and coherent modeling actions. Large Language Models (LLMs)
why not? what in the current harnesses are not bitter lesson-pilled? off top of head: will go away: - planning tools - compaction (or at least will matter less) not going away: - sub agents - skills -
ServiceNow Inc. today announced a sweeping overhaul of its entire product lineup, saying that every single one of its services, platforms and products has been “AI-enabled” to enhance agentic automati
Someone recently suggested to me that the reason OpenClaw moment was so big is because it's the first time a large group of non-technical people (who otherwise only knew AI as synonymous with ChatGPT
If you're an AI/agent builder, it's so important that you don't overbuild and overcommit on a specific toolset and infrastructure. Frontier labs are shipping not just the models, but the harnesses and
So much alpha on the TL today, but this has to be the💧that you should take a minute to read @Vtrivedy10 pitching an incredible approach to auto-improving systems, something i've been experimenting wit
This uses LiteParse, which is great for fast text search: https://developers.llamaindex.ai/liteparse/?utm_medium=social&utm_source=xjl If you're interested in deeper VLM-enabled search, check out Llam
Week 3 ends tomorrow night. $5K up for grabs. Don’t miss your chance. $20,000 up for grabs. 4 weeks. 4 winners. We’re launching the Agent 4 Content Challenge. Build something. Film it. Post it. That’s
✈ DeepSeek-V4.1-Flash-1017 is on Ollama! US-based hosting with zero data retention. It's strong on agentic tasks while being cheaper per task. Try it on Ollama Cloud: ollama run deepseek-v4.1-flash:10
arXiv:2610.21794v1 Announce Type: new Abstract: Despite the remarkable generalization capabilities of Large Language Models, generating clinically accurate and structured radiology reports from medica
arXiv:2610.21345v1 Announce Type: new Abstract: Agentic knowledge graph question answering(KGQA) relies on sequences of executable operations, but trajectory-level rewards obscure their individual con
Meta Platforms Inc. today released open weights for its Muse Spark artificial intelligence model, which had been proprietary since its April debut. The release, called Muse Spark Open, is built for co
Meta’s Muse Spark Open is an 816‑billion‑parameter mixture‑of‑experts coding model that activates only 42 billion parameters per token through top‑8 routing across 256 experts, and has been trained on
arXiv:2610.19316v1 Announce Type: cross Abstract: Assigning routine tasks to cheaper large language model (LLM) providers can reduce generation cost, but switching providers may require processing acc
arXiv:2610.17651v1 Announce Type: cross Abstract: Recent coding large language models (LLMs) can synthesize dynamic 4D worlds from natural language, but the resulting content remains a visual artifact
arXiv:2610.14609v1 Announce Type: new Abstract: Determining whether an image is AI-generated does not establish whether the situation it depicts is factually supported. We formulate Image Factuality A
arXiv:2610.18307v1 Announce Type: new Abstract: Service and delivery robots often need to complete long-horizon navigation missions spanning indoor and outdoor environments. Existing embodied navigati
arXiv:2610.17089v1 Announce Type: new Abstract: Existing embodied navigation tasks commonly assume that traversability and object states remain fixed during an episode. Yet reaching a goal may require
arXiv:2610.14000v1 Announce Type: new Abstract: Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When every t
arXiv:2610.13479v1 Announce Type: new Abstract: Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase s
arXiv:2610.12793v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because
arXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still
With only ~$1,000 of training compute, we trained 𝗳𝗿𝗼𝗺 𝘀𝗰𝗿𝗮𝘁𝗰𝗵 a 1.7B coding agent that beats Claude 3 Opus and GPT-4o on SWE-bench Verified 🤯 At 25.5% pass@1, it sets a new record for nanoswe, our op
arXiv:2610.12002v1 Announce Type: cross Abstract: Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settin
arXiv:2610.11451v1 Announce Type: new Abstract: We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows.
arXiv:2610.11650v1 Announce Type: cross Abstract: Similar agent skills can share instructions but differ in their conditions of use. Query-based text selection may retain shared instructions and omit
arXiv:2610.11171v1 Announce Type: cross Abstract: Long-form video understanding often involves multiple questions about different aspects of the same recording. Yet existing video agents typically pro
arXiv:2610.10611v1 Announce Type: new Abstract: Agentic AI systems can improve by searching longer, receiving additional support, or modifying how they propose and verify outputs. A performance score