Search: “agents”

arXiv:2610.08954v1 Announce Type: new Abstract: Video large language models (Vid-LLMs) excel at diverse video-language tasks by reasoning over selected frames. However, frame selection for long videos

arXiv:2610.07982v1 Announce Type: new Abstract: Monocular metric depth estimation and 3D visual grounding represent the two complementary cornerstones of monocular 3D spatial understanding (M3Sun), fr

arXiv:2610.08250v1 Announce Type: new Abstract: Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation re

OCR is the perfect example of a use case that has been dominated by legacy/brittle systems, and can be solved both accurately and cheaply by applying the right amount of agentic intelligence. A proper

arXiv:2610.08018v1 Announce Type: new Abstract: Reliable tool use requires more than triggering a mechanism or matching a query to an API description. Before selecting a specific tool, an agent must f

arXiv:2610.05481v1 Announce Type: cross Abstract: Large language models for code generation often fail on execution, multilingual coverage, and contamination control, especially under frozen backbone

arXiv:2610.03330v1 Announce Type: cross Abstract: We consider a distributed learning task with agents that have correlated data. Specifically, the label of an agent depends on the input of other agent

Let's go https://huggingface.co/reflection! Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active. - Frontier reasoning efficiency - Advances the Western op

arXiv:2610.02740v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental

arXiv:2610.02404v1 Announce Type: cross Abstract: We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simpl

Banger paper from Meta Superintelligence Labs. They find something super interesting and unexpected. (bookmark it) Base models with a light harness often solve more agentic tasks than their RL post-tr

First AutoHarness, then AutoContext, now AutoCompact. I am seeing a rising trend of work that trains models to natively support more of what the harness does. This work specifically trains agents to d

Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, the

arXiv:2610.01509v1 Announce Type: new Abstract: An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of

This Week in Replit 1) Interactive charts are now in Replit chat. Why is this quarter's pipeline falling short? Which channels are performing best? Just ask Replit Agent 'let's visualize this' and get

arXiv:2609.38335v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories. Ho

arXiv:2609.38516v1 Announce Type: cross Abstract: Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work

arXiv:2504.04711v2 Announce Type: replace Abstract: Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes defini

arXiv:2609.38397v1 Announce Type: new Abstract: Virtual clients offer a cost-effective approach to support applications such as A/B testing, recommender system development, and interface evaluation. H

arXiv:2609.39578v1 Announce Type: new Abstract: Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly const

arXiv:2609.34951v2 Announce Type: replace Abstract: In 2023, AI models answered from training data and hallucinated when it ran out, and businesses were told to seed that knowledge. Models' training k

arXiv:2609.37223v1 Announce Type: new Abstract: Credit-risk prediction is important in banking, but a prediction alone does not explain why an applicant is risky or how it should be combined with othe

Building on nearly a decade of co-engineering, CoreWeave has built NVIDIA compute, networking and software into a cloud purpose-built for AI that’s still returning on investment across multiple genera

arXiv:2609.36490v1 Announce Type: cross Abstract: Latent space monitors aim to detect undesired behaviors in LLM agents by inspecting an agent's internal activations rather than its outputs. However,

arXiv:2609.36879v1 Announce Type: cross Abstract: As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent S

arXiv:2609.34484v1 Announce Type: cross Abstract: Progress reward modeling is the problem of estimating how a robot's behavior changes task progress over time. Reliable estimation requires distinguish

arXiv:2609.35530v1 Announce Type: new Abstract: Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation

arXiv:2605.05386v2 Announce Type: replace-cross Abstract: Large language models increasingly operate in interactive settings where solving a task requires multiple rounds of information exchange with

Opening a Model Context Protocol server, or MCP server, to customers’ AI tools is becoming standard for fintech companies, but in payments a rogue agent does not just leak data — it moves money. That

OpenAI disclosed that an experimental, internal model was prompted to research Victoria’s government spending data. Unable to locate the information publicly, the model performed unauthorized actions,

arXiv:2609.31718v1 Announce Type: cross Abstract: Images often carry recommendation constraints that text metadata only hints at. A movie may need to look dark, a product may need a minimal style, and

arXiv:2609.30541v1 Announce Type: new Abstract: Optimizing embedding systems for production recommendation pipelines demands systematic exploration that consumes disproportionate engineering effort at

arXiv:2609.30906v1 Announce Type: new Abstract: Large language models (LLMs) excel at natural language processing but struggle to interact with external environments. Tool learning provides a promisin

Quite the combination of arrogance and incompetence over there at OpenAI: Yup, part of the transformation of enterprise architects into orchestrators is the technical ability to put guardrails on AI a

In this project I wanted to see if any interesting emergent behaviors would appear if we trained two agents to play a streetfighter-like game using RL. Maybe obvious in retrospect, but the agents are

The Top AI Papers of the Week (September 21 - 27): - HySparse2 - EvoOntology - Harness-Zero - JEV-as-a-Judge - Wiki Foundation Model - Self-Organizing Agent Teams - Self-Improvement via Fast Tree-sear

This is brilliant. Recommended reading. It's a great example of how you could potentially build more effective harnesses using System One and System Two models. It explores Jev's potential as a fuzzy

Banger paper from Microsoft and colleagues. We talk about human taste being important in this AI era. But for recursive self-improvement, an agent's taste also matters. The big question is: How often

arXiv:2609.30059v1 Announce Type: cross Abstract: Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically

arXiv:2609.29341v1 Announce Type: new Abstract: Consumer-facing skincare AI must coordinate visual evidence, product information, tool use, and user-facing actions within explicit evidence and safety

arXiv:2609.27123v1 Announce Type: new Abstract: Heterogeneity across Collaborative Perception (CP) agents is a major challenge for emerging CP frameworks due to domain gaps from differing sensors, arc

arXiv:2609.22719v1 Announce Type: cross Abstract: Business requirements for enterprise software systems are rarely captured in structured form; the logic resides instead in source code, configuration

arXiv:2609.26520v1 Announce Type: new Abstract: Humanoid robots require diverse embodied experiences to acquire complex loco-manipulation and collaborative skills. However, existing humanoid data pipe

arXiv:2609.24362v1 Announce Type: new Abstract: Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language mo

ROS 2 nodes in NVIDIA Isaac ROS 5.0 now employ a CUDA buffer backend (via rosidl::Buffer) so that payloads remain GPU‑resident and can be transferred between nodes with zero‑copy when both endpoints s

arXiv:2609.24127v1 Announce Type: new Abstract: Atomic activity understanding aims to recognize and localize structured traffic behaviors that jointly encode motion patterns and their grounding in roa