A new arXiv paper re-estimates METR's AI time horizons using splines and item-response theory on 228 tasks and 26 AIs, finding that the difficulty curve is nearly flat between 2 and 30 minutes. This means a jump from 3 to…

#AI #DevTools #SoftwareEngineering #ArXiv
https://arxiv.org/abs/2610.12466

New arXiv paper ReCast proposes a step representation learning method to improve failure attribution in LLM-based agent systems by transforming hidden states from a frozen LLM into attribution-oriented representations.

#AI #LLMAgents #Research #ArXiv
https://arxiv.org/abs/2610.11334

Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models

Lars Simon, Holger Eble, Manuel Radons

#arXiv #cs.AI #cs.LG #cs.LO

Q-Shaped Options for Hierarchical Reinforcement Learning

Clarisse Wibault et al.

#arXiv #cs.AI

EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution

Yanning Dai et al.

#arXiv #cs.AI

Onboard Marine Anomaly Detection on $\Phi$sat-2: From Simulation-Based Development to In-Orbit Demonstration

Clotilde Szywala et al.

#arXiv #cs.AI #cs.CV

Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games

Nick Leenders et al.

#arXiv #cs.AI

AgentEvolver: System-Wide Self-Evolution Through Task Execution

Wentao Zhang et al.

#arXiv #cs.AI

RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees

Meghanadh Pulivarthi et al.

#arXiv #cs.AI #cs.IR

RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty

Gukhyeon Lee, SangKeun Lee

#arXiv #cs.AI #cs.CL #cs.LG

SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning

Wei Yang et al.

#arXiv #cs.AI

Plan-and-Patch: Diffusion Language Models for Agentic Planning

Syamantak Kumar et al.

#arXiv #cs.AI #cs.CL #cs.LG

An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment

Marcelo Valentim Silva, Hannes Herrmann, Valerie Maxville

#arXiv #cs.AI #cs.CL

A masked generative transformer with geometry-guided token search extends learned trajectory priors into discrete structural repair, turning motion planning refinement into an efficient search over alternatives.…

#Arxiv #Robotics #MotionPlanning #GenerativeAI
https://arxiv.org/abs/2610.10646

New arXiv paper formalizes Abductive Autonomous Scientific Discovery (AASD) using possibility theory, introducing abductive utility and possibility frontier search as an anytime-valid algorithm for LLM-driven…

#AI #ScientificDiscovery #MachineLearning #ArXiv
https://arxiv.org/abs/2610.11289

🔭 Radar arXiv del Día | Frontera Científica

¿Qué secretos esconde el borde de un agujero negro? Nuevos datos con ondas gravitacionales nos permiten escuchar el eco del horizonte. ¡Fascinante!

📄 "Listening t...
👉 Ver en Radar LOGIDIAS
#arXiv #Ciencia #CienciaÑ #SciSky #Física #Física

Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models

Lars Simon, Holger Eble, Manuel Radons

#arXiv #cs.AI #cs.LG #cs.LO

Q-Shaped Options for Hierarchical Reinforcement Learning

Clarisse Wibault et al.

#arXiv #cs.AI

EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution

Yanning Dai et al.

#arXiv #cs.AI

Onboard Marine Anomaly Detection on $\Phi$sat-2: From Simulation-Based Development to In-Orbit Demonstration

Clotilde Szywala et al.

#arXiv #cs.AI #cs.CV