agents

arXiv:2609.32783v1 Announce Type: cross Abstract: Before a team of robots moves, each proposed step must be checked for collisions with other robots and with obstacles. We present CollisionGAT, a grap

arXiv:2609.31989v1 Announce Type: cross Abstract: We study communication between two frozen large language models from different providers, with different tokenizers, accessed through their API endpoi

🚨🔥 Congress (@RepJoshG @ValerieFoushee @tedlieu) to OpenAI, Anthropic, Google, Meta, SpaceX on their inadequate reporting of their inadequately-controlled agents: “Your companies have since notified t

arXiv:2609.35152v1 Announce Type: cross Abstract: Successive weaving segments (SWSs) on urban expressways are bottlenecks prone to recurrent congestion and collisions, requiring fine-grained active tr

arXiv:2609.31873v1 Announce Type: new Abstract: Keyframe selection (KFS) has long produced compact video summaries for browsing and retrieval, and representative frames for thumbnails. More recently,

arXiv:2609.31893v1 Announce Type: new Abstract: Deep reinforcement learning has become a prominent approach to autonomous cyber defense. Existing methods are predominantly model-free and consequently

arXiv:2609.33768v1 Announce Type: new Abstract: Multi-agent systems (MAS) have recently emerged as an effective approach for coordinating large language model (LLM)-based agents to solve complex tasks

arXiv:2609.32805v1 Announce Type: cross Abstract: Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits. A growing line o

arXiv:2609.35525v1 Announce Type: new Abstract: Principled exploration in reinforcement learning requires an agent to quantify its epistemic uncertainty and act to resolve it. Uncertainty over the val

arXiv:2609.31885v1 Announce Type: new Abstract: Autonomous micro-mobility vehicles (MMVs) such as wheelchairs, scooters, and bicycles have the potential to improve mobility access and support safe low

arXiv:2603.18257v3 Announce Type: replace Abstract: When an RL agent's observations contain distractors driven by the same confounders as its true state, observational data alone cannot identify which

arXiv:2602.08847v2 Announce Type: replace Abstract: Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for s

arXiv:2609.35047v1 Announce Type: cross Abstract: A robot should be able to learn through experiments how unfamiliar objects behave and interact, then plan with that knowledge. It need not start from

arXiv:2609.33939v1 Announce Type: cross Abstract: Reliable 3D spatial understanding is essential for autonomous navigation, obstacle avoidance, and scene reconstruction. While state-of-the-art learned

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

arXiv:2609.34719v1 Announce Type: new Abstract: Autonomous excavation requires a spatial representation that jointly captures terrain geometry and task-relevant semantics. Existing excavation mapping

arXiv:2211.14393v2 Announce Type: replace Abstract: We study the problem of learning a linear system model from the observations of M clients. The catch: Each client is observing data from a different

arXiv:2609.32855v1 Announce Type: cross Abstract: Adapting vision-language navigation (VLN) policies to new environments is expensive because every additional route and instruction requires an embodie

Artificial intelligence is changing the makeup of internet traffic, making AI identity an emerging concern for websites and applications. They are no longer interacting only with humans and traditiona

Here's a metric dashboard giving an idea of the last few days. Been testing with a variety of different agentic coding use-cases, mostly using a pi harness. qwen3.8-flash-next has seriously exceeded m

arXiv:2609.35728v1 Announce Type: new Abstract: We present FlowAct-R2, a framework for interactive humanoid video generation that combines continuous multimodal control with proactive agent planning.

arXiv:2609.33190v1 Announce Type: new Abstract: Driving decisions depend on both where to focus and how to act on what is seen. Effective driving reasoning must establish which objects matter, where t

arXiv:2609.34198v1 Announce Type: new Abstract: Language-model judges compare agent upgrades with their predecessors, but a fixed judge can make version-dependent mistakes. We analyze 35 public coding

arXiv:2609.31901v1 Announce Type: new Abstract: Constrained general-sum dynamic games are a popular formulation for highly interactive multi-agent planning problems. In recent years, Generalized Nash

arXiv:2609.34633v1 Announce Type: new Abstract: Long-term memory supports the self-evolution of LLM agents by retaining experience and skills across tasks and enabling their retrieval, reuse, and revi

Great paper from Amazon AGI on generating RL environments for agents. (bookmark it) Also, pay attention to this important new AI engineering skill of creating RL environments. Seeing a huge shift towa

arXiv:2606.18363v2 Announce Type: replace Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodi

arXiv:2609.35038v1 Announce Type: cross Abstract: Federated Bayesian Optimization (FBO) enables distributed agents to collaboratively optimize expensive black-box objectives without sharing raw local

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:2609.33986v1 Announce Type: new Abstract: In some multi-agent systems, the quantity to be optimized is not an externally specified reward but the information acquired about unknown properties of

arXiv:2110.15075v2 Announce Type: replace Abstract: Estimating causal effects from observational data informs us about which factors are important in an autonomous system, and enables us to take bette

Every major security shift ultimately comes down to one question: Who or what is allowed to do this? For most of the past two decades, the answer was a person with a username and password. In the arti

arXiv:2609.31929v1 Announce Type: new Abstract: Newton methods efficiently find Generalized Nash Equilibria (GNE) in dynamic games by solving for the KKT necessary conditions. These methods are fast a

arXiv:2609.33288v1 Announce Type: new Abstract: Embodied Question Answering (EQA) requires agents to answer natural language questions about surrounding environments from visual observations. In this

arXiv:2609.32048v1 Announce Type: new Abstract: Model misspecification poses a fundamental challenge in multi-agent reinforcement learning, where transition uncertainty can be amplified by strategic i

Agent Builders Night, organized by KERNEL in partnership with Braintrust and Llama Index, is scheduled for this evening at 6 pm on September 29, 2026. The event features drinks, demo showcases, and ne

arXiv:2609.34045v1 Announce Type: cross Abstract: Between them, the members of a research group or a circle of friends own several consumer computers, none large enough to run a capable large language

Big data management company Komprise Inc. is trying to make life easier for artificial intelligence agents and large language models that leverage the open-source Model Context Protocol to access thir

LA Tech Week is coming up in two weeks, and we’re doing our monthly LA Agentic AI Meetup during it. Tuesday, October 13 at Gulp in Playa Vista. 5–7pm. A few live demos, drinks, and a bunch of real peo

listen is a great company, alfred and florian are awesome founders the problem space listen is tackling is also an amazing use case for AI, very bullish on what they will still build here! Listen Labs

arXiv:2609.34491v1 Announce Type: new Abstract: Small-molecule optimization integrates medicinal-chemistry reasoning and computational evidence through iterative, multi-objective decisions. When large

arXiv:2609.33563v1 Announce Type: new Abstract: World models improve sample efficiency by training policies on imagined trajectories, but their usefulness depends on learning representations that capt

arXiv:2609.32874v1 Announce Type: cross Abstract: The first sentence of this abstract--and the introduction to these proceedings--was authored by a human, but the bulk of this document was generated b

arXiv:2609.31789v1 Announce Type: cross Abstract: In this work, we explore MammoClaw, a training-free agent framework that leverages frozen MLLMs for mammography analysis. To support agentic investiga

arXiv:2609.34378v1 Announce Type: new Abstract: Humans naturally possess the ability to work persistently toward long-term goals. Given a challenging task, humans can continuously work for months or e

arXiv:2609.32379v1 Announce Type: new Abstract: What controls are needed to interpret execution performance and audit scores in LLM agent evaluations? We study two limits on these interpretations in a