agents

Enterprise software veterans have become all too familiar with the gap between flashy artificial intelligence demos and their performance in real-world production environments. The reality is that a l

Cognition AI is promoting an auto-triage feature or tool available at devin.ai/auto-triage, inviting users to test it. The tool likely automates the process of categorizing, prioritizing, or routing i

very belated but in retrospect i think @sama's mythical 'build a business that gets better when models get better' is basically what I called Agent Labs here. seeing a very direct correlation with mod

Very cool - Grok Build is clearly getting better by the day. Two nights ago I ran an overnight build and it failed. Last night, success. I really like the multi-agent orchestration behavior, it does a

arXiv:2605.20082v1 Announce Type: cross Abstract: The rapid growth of autonomous driving datasets has enabled the scaling of powerful motion forecasting models. While large-scale pretraining provides

We are also launching Science Skills, a specialized bundle that integrates insights from 30+ major life science models and databases with agentic platforms like @Antigravity to allow researchers to pe

We built an AI agent for due diligence, with exact audit trails back to the source page, that you can use as a template without paying a single dime for PDF parsing 🔥🆓 The secret sauce is LiteParse -

Exa, a search lab focused on organizing web data for AI agents, announced a Series C funding round of 250 million at a 2.2 billion valuation, led by venture capital firm Andreessen Horowitz (a16z). Th

We ran 720 browser agent tasks with @nottecore across frontier models. One baseline model produced malformed outputs in ~1 out of every 5 calls, leading to retries inside multi-step workflows. Across

We’re hiring for Labs! 🧪 If you’re interested in working with us to push forward Continual Learning, pls DM me with a blurb + link to the best Applied Research you’ve done (or even better shipped!) yo

we've been building agents around the llm, starting with conversations, adding tools, giving rules, logging everything, and storing a form of it as retrievable state Active Graphs flips this. what if

arXiv:2605.19447v1 Announce Type: new Abstract: Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failur

When an agent is allowed to decompose a goal into smaller sub-tasks, it frequently suffers from goal drift. Left unchecked, it will redefine the optimization metric to favor a simpler, useless sub-tas

arXiv:2605.18858v1 Announce Type: cross Abstract: Probabilistic prediction systems often aggregate probability estimates from multiple models into a single decision. A common assumption is that if eac

arXiv:2605.20023v1 Announce Type: new Abstract: Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by

arXiv:2605.19261v1 Announce Type: cross Abstract: Ensuring the reliability and resilience of modern web applications remains a critical challenge due to increasing system complexity and dynamic runtim

WisdomAI Inc., creator of an artificial intelligence-native business intelligence platform, is jumping on the agentic AI bandwagon with the latest update to its flagship Federated Agentic Intelligence

working on some hex dashboards -- this is a bummer! if you use langchain/deepagents as your agent harness, you can swap models with fallback middleware when your first choice provider is down https://

arXiv:2509.19182v2 Announce Type: replace-cross Abstract: Incorporating natural language input has the potential to improve the capabilities of biomedical data discovery interfaces. However, user inte

You can also now create automations without any attached repos, like a daily Slack digest agent that prioritizes unread threads and DMs for your response. Find more templates in our marketplace: http:

you can condense long horizon evals with agents into smaller subsets that still let you test intended behavior. i'm currently evaluating an agent that runs for 30+ minutes, and analyzes thousands of t

You can now create and manage automations in the same workspace as your agents. Automations are now available in the Agents Window. For the next 7 days, all agent runs for newly created automations ar

You can set up Auto-Triage for any Slack channel with just three clicks. To help get you started, we're offering $200 in credits when you create your first Devin Automation. Media Introducing Devin Au

arXiv:2605.16522v1 Announce Type: new Abstract: Collective behavior in animals has long been modeled through self-propelled particle models, which reproduce striking group-level phenomena through abst

arXiv:2503.12181v4 Announce Type: replace Abstract: Online planning in continuous state, action, and observation spaces remains challenging for autonomous systems. While Monte Carlo Tree Search (MCTS)

arXiv:2602.03955v2 Announce Type: replace Abstract: While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limite

arXiv:2605.17041v1 Announce Type: cross Abstract: We present Agentic AI Translate, an agentic translator prototype that operationalises the thesis of Yamada (forthcoming) -- that the metalanguage of T

arXiv:2605.17831v1 Announce Type: new Abstract: Query optimization in big data analytics remains computationally expensive, particularly for resource-constrained environments where traditional optimiz

arXiv:2605.16419v1 Announce Type: cross Abstract: Kinematic monitoring plays a critical role in long-term rehabilitation for patients with spinal cord injury (SCI), where multi-view markerless motion

Enterprises racing toward assured autonomy in agentic AI are running headlong into a decades-old problem: Most of their infrastructure was never designed to be connected — let alone governed at the sp

arXiv:2605.17746v1 Announce Type: new Abstract: AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and oper

arXiv:2605.17123v1 Announce Type: cross Abstract: At a time when drones are increasingly associated with hostile operations, we re-purpose them for humanitarian and life-saving applications. However,

This post likely documents the technical architecture and development process behind Engine, a software component or platform, shared by Palash Shah. The content presumably covers key design decisions

arXiv:2605.16725v1 Announce Type: new Abstract: Executable world models can be read, edited, executed, and reused for planning, but only if the program captures the environment's transition law rather

Multi-agent orchestration is the destination, but for most enterprises, the road is blocked long before the first agent gets deployed by the quality of the data feeding those systems. As organizations

arXiv:2603.23672v2 Announce Type: replace-cross Abstract: Biological sensory systems are inherently adaptive, filtering out constant stimuli and prioritizing relative changes, likely enhancing computa

You can build a measurably better agent from data you already have, without retraining a thing. The data is what your experienced humans do when they correct the AI. Capture... The post Building a sel

arXiv:2602.16699v3 Announce Type: replace-cross Abstract: LLM agents are deployed in environments where they must interact to acquire information. In these scenarios, the agent must reason about inher

arXiv:2603.23638v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly tested on complex tasks, but their ability to allocate scarce resources over long horizons remain

arXiv:2307.09575v2 Announce Type: replace-cross Abstract: This paper investigates causal influences between agents linked by a social graph and interacting over time. In particular, the work examines

arXiv:2504.16397v2 Announce Type: replace-cross Abstract: The rise of compound AI serving that integrates multiple operators in a pipeline enables end-user applications such as generative AI-powered m

arXiv:2511.11654v2 Announce Type: replace-cross Abstract: Rapid urbanization in cities like Bangalore has led to severe traffic congestion, making efficient Traffic Signal Control (TSC) essential. Mul

arXiv:2604.01658v2 Announce Type: replace Abstract: Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge

Curious finding while creating evals and benchmarks for long-horizon (100+ turn) agents While it’s generally thought that a direct swap to open source models can bring immediate cost savings, that’s n

Cursor is now available in Jira. Assign Cursor to work items, or mention @​Cursor in a comment to kick off a cloud agent. Cursor uses the title, description, comments, and your team's repository setti

arXiv:2605.16298v1 Announce Type: cross Abstract: While traditional AI and data-driven facilities management approaches have improved building operational efficiency, they remain constrained by centra