arXiv:2604.02375v1 Announce Type: new Abstract: Tool-calling autonomous agents based on large language models using ReAct exhibit three limitations: serial latency, quadratic context growth, and vulnerability to prompt injection and hallucination. Recent work moves towards separating planning from execution but in each case the model remains coupled to the execution mechanics. We introduce a system-level abstraction for LLM agents which decouples the execution of agent workflows from the LLM reasoning layer. We define two first-class abstractions: (1) Intent-Gated Execution […]

Ver mais

A Guide to Racing online with Gran Turismo 7 Going online to multiplayer in Gran Turismo 7 is one of the biggest attractions in the game. In single-player mode, the opponents are predictable. You can practice a track for hours, perfect your lines, and gradually build your pace. But the moment you enter an online race, everything changes. You’re now sharing the track with 15 other real human drivers who race like real people. They brake late, defend aggressively, make […]

Ver mais

arXiv:2606.07790v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on communication protocols for coordination, yet their robustness under adversarial and structural constraints remains poorly understood. Building on prior work showing that cheap-talk channels enable cooperation in LLM coordination games, we investigate two vulnerability classes in a 4-player Stag Hunt across six model families and 720 trials. First, when Byzantine agents signal cooperation but defect, non-Byzantine agents detect the betrayal within one round yet fail to adapt collectively: […]

Ver mais

I think we will see some people employed (though perhaps not explicitly) as meat shields: people who are accountable for ML systems under their supervision. The accountability may be purely internal, as when Meta hires human beings to review the decisions of automated moderation systems. It may be external, as when lawyers are penalized for submitting LLM lies to the court. It may involve formalized responsibility, like a Data Protection Officer. It may be convenient for a company […]

Ver mais

arXiv:2601.12220v1 Announce Type: new Abstract: We present an algorithm for normalizing emph{Batched Einstein Summation} expressions by mapping mathematically equivalent formulations to a unique normal form. Batches of einsums with the same Einstein notation that exhibit substantial data reuse appear frequently in finite element methods (FEM), numerical linear algebra, and computational chemistry. To effectively exploit this temporal locality for high performance, we consider groups of einsums in batched form. Representations of equivalent batched einsums may differ due to index […]

Ver mais

Recent years have witnessed the widespread adoption of reinforcement learning (RL), from solving real-time games to fine-tuning large language models using human preference data significantly improving alignment with user expectations. However, as model complexity grows exponentially, the interpretability of these systems becomes increasingly challenging. While numerous explainability methods have been developed for computer vision and natural language processing to elucidate both local and global reasoning patterns, their application to RL remains limited. Direct extensions of these methods often […]

Ver mais

arXiv:2602.13311v1 Announce Type: new Abstract: In industrial millimeter-wave (mmWave) multi-hop Integrated Access and Backhaul (IAB) networks, dynamic blockages caused by moving obstacles pose a severe threat to robust and continuous networks. While Packet Duplication (PD) enhances reliability by path diversity, it inevitably doubles the traffic load, leading to severe congestion and degraded Age of Information (AoI). To navigate this reliability-congestion trade-off, we formulated an optimization problem in a multi-hop IAB scenario that minimizes the average AOI while satisfying […]

Ver mais