agents

Great paper from AWS. I use a similar setup where an agent orchestrator sits on top of a multi-agent system. (bookmark it) This work introduces one of the many approaches available to manage compound

arXiv:2609.09752v1 Announce Type: new Abstract: Automatic Guided Vehicles (AGVs) substantially boost warehouse throughput, but routing large-scale AGV fleets remains challenging. Classical Multi-Agent

arXiv:2609.10123v1 Announce Type: cross Abstract: Large language models (LLMs) have become ubiquitous in software development, with LLM-based automated program repair tools increasingly used during co

If you ask a coding agent to write a program that maps x to y given some (x, y) examples, you're doing a very expensive form of symbolic learning. In fact what you're doing is specifically a form of D

If you run automated prompt or harness evolution, this one is worth your time. (bookmark it) Semantic-gradient prompt optimization improves an agent harness from execution feedback, but its local upda

arXiv:2609.06792v1 Announce Type: new Abstract: Android agents using a hybrid action space that combines GUI actions and tool actions (e.g., accessing application data via APIs) remain largely underex

arXiv:2609.05774v1 Announce Type: new Abstract: Recent multi-agent LLM systems increasingly rely on graph-structured communication to coordinate specialized agents. We revisit multi-agent orchestratio

arXiv:2609.06250v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) process large amounts of tickets, most of which are low-interest events not worthy of further investigation. The re

Identity and access management company JumpCloud Inc. today extended its Agentic IAM service to give information technology teams direct control over the autonomous artificial intelligence agents runn

arXiv:2609.10266v1 Announce Type: new Abstract: LLM serving systems already reuse KV caches, but only when the reused text sits at the very start of the prompt. Two growing workloads break this condit

arXiv:2510.05124v3 Announce Type: replace Abstract: We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS emp

arXiv:2609.09115v1 Announce Type: new Abstract: Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interacti

arXiv:2609.08273v1 Announce Type: new Abstract: Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuou

arXiv:2609.09791v1 Announce Type: new Abstract: With hate speech being ubiquitous online, automatic detection is crucial, in particular when it comes to criminally relevant social media posts. We stud

Now everyone can put data to work. We’re introducing a new Data agent in ChatGPT Work so you can turn your company’s data into answers, interactive dashboards, and action—just by asking. Just add the

arXiv:2609.09809v1 Announce Type: new Abstract: In online inverse linear optimization, the learner predicts a weight at each round, observes the optimal action of the agent, and updates its prediction

A deep research agent has to do more than answer a question. It plans, searches, opens documents, gathers evidence, reasons across sources, and keeps going across dozens or hundreds of tool calls befo

arXiv:2609.08558v1 Announce Type: new Abstract: Personalized memory helps LLM agents deliver stable, tailored assistance by storing and reusing user-specific data across interactions. In multi-user sc

arXiv:2605.21694v2 Announce Type: replace-cross Abstract: Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender

Recommended read. As the world becomes more agentic, we will start to see world models of different shapes. As an example, I find this “business world model” from @lightfld fascinating as a way to mod

arXiv:2609.08062v1 Announce Type: new Abstract: Tool-using language agents can delegate and revoke permissions while acting through external services. We show that two authorization histories can have

arXiv:2609.08175v1 Announce Type: new Abstract: Harness self-evolution is the process by which an agent modifies its prompts, tools, code, or orchestration in response to task feedback while keeping t

arXiv:2502.14043v3 Announce Type: replace Abstract: Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cann

arXiv:2609.06124v1 Announce Type: new Abstract: High-quality multi-turn tool-use data is essential for training agentic models, yet existing data synthesis methods often underrepresent the argument-le

arXiv:2609.08944v1 Announce Type: new Abstract: Agent skills provide a lightweight way to equip frozen language-model agents with domain knowledge and procedural guidance, yet obtaining high-quality s

arXiv:2609.09764v1 Announce Type: new Abstract: Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collabo

arXiv:2609.06128v1 Announce Type: new Abstract: Production LLM agents execute tool-calling loops, retrieval chains, and compositional workflows in multiple modes, yet execution semantics are often cou

Meta has launched its new Muse assistant, marking the company's first real foray into AI-powered productivity tools. The company says its AI agent can 'take the busywork off your plate' by helping you

arXiv:2609.05631v1 Announce Type: cross Abstract: A voice agent has to decide, at every pause, whether the user has finished speaking. Without a model of the language that decision falls back to a fix

arXiv:2609.05643v1 Announce Type: new Abstract: This Comment emerges from TPC26 (https://tpc26.org), a conference convening leaders from academia, national laboratories, and industry who are reshaping

arXiv:2609.05894v1 Announce Type: new Abstract: The exponentiation of Artificial intelligence (AI) in the recent past has entered a transformative era that has been driven by the growth in large langu

arXiv:2609.07478v1 Announce Type: new Abstract: Large language models act as strategic agents and models of human choice, yet choosing like a strategic agent does not mean computing like one. We recor

The Replit-Databricks integration is now generally available, with new native Lakebase support! Now, you can use @Replit to build full-stack Databricks Apps on live, governed enterprise data. Replit A

this is what i was talking about earlier when you're young you try to design the perfect system with neat rules that guarantee stability eventually you learn that real stability comes from messy, orga

arXiv:2609.09056v1 Announce Type: new Abstract: Modern science and engineering increasingly rely on time-varying data, yet the mathematical tools used to model temporal phenomena are often developed w

arXiv:2602.12566v4 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LL

arXiv:2601.18930v5 Announce Type: replace Abstract: We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms. We cast this probl

arXiv:2609.09815v1 Announce Type: cross Abstract: Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the fina

arXiv:2609.05920v1 Announce Type: cross Abstract: Agent Skills combine instructions with files, packages, tools, models, and services, so operational identity can exceed a signed directory. Recursive

arXiv:2609.09985v1 Announce Type: new Abstract: Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a f

We've trained new models for checkbox parsing ☑️ This lets you convert checkboxes of any size and shape, filled or unfilled, into structured JSON that's suitable for programmatic or agentic use. Use i

arXiv:2504.00285v2 Announce Type: replace Abstract: Large Language Models (LLMs) are effective at deceiving when prompted to do so. Models that demonstrate better performance on reasoning tasks are al

arXiv:2609.09628v1 Announce Type: cross Abstract: Inferring speaker relationships from spoken conversations is an important step towards socially aware speech understanding. However, this task remains

arXiv:2609.05677v1 Announce Type: cross Abstract: Lifelong LLM agents increasingly rely on external skill artifacts as one element for preserving and reusing capabilities over time. These skills (usua

arXiv:2609.08162v1 Announce Type: new Abstract: How can vision-language-action (VLA) models adapt to new environments where world dynamics shift? While recent research has combined world modeling and

arXiv:2609.09066v1 Announce Type: new Abstract: Maritime target tracking over large distances often requires multi-agent teams without centralized coordination, and intermittent communication. Each ag