agents

Cloud security startup Upwind Security Inc. today unveiled AI Agent Context Scanner, which inspects the instructions, tools and connections feeding artificial intelligence agents before those agents a

arXiv:2607.26637v1 Announce Type: new Abstract: Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, an

Finally a good paper testing if file-system based memory for LLM agents is worth it. First, what does this look like? Deployed agents keep long-term memory as a folder of markdown files they read and

arXiv:2607.26492v1 Announce Type: new Abstract: The Mass-Conserving Perceptron (MCP) establishes a modeling paradigm in which conceptual hydrologic models can be reformulated as physically constrained

arXiv:2607.26283v1 Announce Type: new Abstract: Collaborative Perception (CP) improves autonomous systems' awareness of their surroundings by sharing sensor data, intermediate features, and detection

arXiv:2607.26375v1 Announce Type: new Abstract: Coding agents (e.g., Cursor) improve developer productivity by optimizing task completion, but shifting users from writing code to prompting and reviewi

Interesting data from the OpenRouter Kimi K3 dashboard: @togethercompute offers one of the lowest prices for @Kimi_Moonshot K3 while also achieving one of the highest prompt cache hit rates. Low prici

Introducing the Parse Gateway There's been an explosion of interest in model routing - you don't always need the best model for every task. That is especially true for document parsing 📄🔀: - Some page

arXiv:2506.10850v2 Announce Type: replace Abstract: Autonomous surface vessels (ASVs) are increasingly vital for marine science, offering robust platforms for underwater mapping and inspection. Accura

In March 2026, Lambda ran AgentBeats, an AI agent security competition in which teams submit two kinds of agents: an attacker that tries to manipulate a target LLM into doing something harmful, and a

arXiv:2607.26598v1 Announce Type: cross Abstract: Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tas

arXiv:2507.02259v2 Announce Type: replace Abstract: Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents with linear complexity with

arXiv:2607.27201v1 Announce Type: new Abstract: World models enable a predictive substrate for planning and action, yet existing formulations merely answer a physical question: what/where it is, and h

arXiv:2607.26345v1 Announce Type: new Abstract: Modeling and forecasting nonlinear dynamics under distribution shifts is essential for robust decision-making in real-world systems. In this work, we pr

arXiv:2607.26760v1 Announce Type: new Abstract: Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal found

arXiv:2607.27146v1 Announce Type: cross Abstract: Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementa

arXiv:2607.27132v1 Announce Type: new Abstract: An agent acting under partial observability must retain a recursively updateable statistic of history that restores the Markov property, but the smalles

arXiv:2607.27036v1 Announce Type: new Abstract: Video diffusion-based world models enable long autoregressive video generation for robotics, autonomous driving and simulation tasks, yet sliding-window

arXiv:2607.26809v1 Announce Type: new Abstract: General-purpose robotic manipulation requires robots to perform diverse tasks in open-world environments while improving their skills over time. Despite

arXiv:2607.26631v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments. Ye

arXiv:2607.27083v1 Announce Type: new Abstract: As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental too

arXiv:2602.19366v2 Announce Type: replace-cross Abstract: We study how to scale distributed bandit submodular coordination under realistic communication constraints in bandwidth, data rate, and connec

arXiv:2607.26570v1 Announce Type: new Abstract: Current spacecraft collision-avoidance operations rely on intermittent ground-station contacts, requiring operators to plan with delayed and asynchronou

arXiv:2603.18271v3 Announce Type: replace Abstract: Ambiguity poses a major challenge to large language models (LLMs) used as robotic planners. In this letter, we present Scene Graph-Chain-of-Thought

arXiv:2606.13317v2 Announce Type: replace Abstract: Skill self-evolution methods for LLM agents aim to turn execution trajectories into reusable skill documents. However, current pipelines typically d

For 6 months now I've been trying to make agentic coding work for me, using Pi and a handful 30-120B models (Qwens, Nemotrons, Leguna...etc). I'm not greedy either, I stick to decent quants, never qua

arXiv:2607.27167v1 Announce Type: cross Abstract: LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fund

arXiv:2607.26273v1 Announce Type: new Abstract: We consider a stochastic multi-objective bandit problem where, at each round, the agent selects a slate of k arms and observes their d-dimensional rewar

arXiv:2607.26410v1 Announce Type: new Abstract: We present Voice Memory, a inference-only scheme for agentic speech recognition: at stream time, a frozen corrector reads a single per-domain memory.md

We have to be careful to not offload our understanding to agents. I think there is also a good opportunity to build agentic applications that encourage deeper understanding. For example, coding agents

We’re excited to rollout an official batch parsing experience to LlamaParse. ✅ Instead of hitting our APIs one file at a time, create a batch of 10k at once. ✅ Get a dedicated UI where you can audit t

arXiv:2607.26497v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) methods range from lexical and dense retrieval to graph-based indexing and agentic search. They are usually evaluat

Hugging Face reported that a recent agent intrusion used Modal’s infrastructure as a launchpad, but Modal’s sandbox isolation was not breached; the malicious code executed only within the affected cus

arXiv:2607.25560v1 Announce Type: new Abstract: Agent skills package reusable procedures that improve downstream performance. Their lightweight, portable form enables marketplace monetization and priv

Agentic inference wastes GPUs on KV cache thrashing. ThunderAgent fixes it at the scheduler level: 2.5x higher single-node throughput and ~10x lower P50 latency at high concurrency. ThunderAgent was a

AI can write more code than any team can review by hand, and a pull request can look fine while hiding a security issue or missing a requirement. In our new short course, AI Code Review, built in coll

This post explains how Private Key JWT client authentication works in AgentCore Identity and reviews the supported grant flows. We then walk through creating an AWS KMS signing key, registering its pu

arXiv:2607.24984v1 Announce Type: cross Abstract: In recent years, the number of events in earthquake catalogs has significantly increased due to the utilization of more effective deep learning based

Learn how to build a no-code customer retention pipeline in Amazon Quick that detects at-risk customers from call transcripts and CSAT data, scores them by retention priority with a custom MCP Action,

Batch parsing used to mean writing API scripts. Now it's a button. 🦙 Parse or extract across up to 10,000 files in one run, straight from the LlamaParse UI. Point it at a folder and go — no code requi

arXiv:2607.25620v1 Announce Type: new Abstract: Quattrociocchi and colleagues warn that the fluent outputs of large language models may allow linguistic plausibility to substitute for epistemic evalua

arXiv:2607.24759v1 Announce Type: new Abstract: Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recov

arXiv:2607.25340v1 Announce Type: new Abstract: The same episode of atrial fibrillation is a minor finding in a healthy adult and grounds for anticoagulation in an elderly patient with hypertension: i

arXiv:2601.03595v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (eg backtracking, cross-verification) during the reasoning process,

arXiv:2607.25379v1 Announce Type: new Abstract: Cyber-capable AI agents combine language models with tools, memory, and execution en- vironments to perform multi-step offensive-security tasks. Existin

arXiv:2607.25554v1 Announce Type: new Abstract: Future event prediction carries broad social impact yet remains challenging. SOTA approaches augment LLMs with external agent frameworks whose predictiv