arXiv:2512.04653v2 Announce Type: replace-cross
Abstract: Multi-agent reinforcement learning (MARL) has emerged as a promising paradigm for adaptive traffic signal control (ATSC) of multiple intersections. Existing approaches typically follow either a…
arXiv:2510.08847v2 Announce Type: replace
Abstract: We introduce the Agent GPA (Goal-Plan-Action) framework, driven by the fundamental insight that critical agent failures emerge at the intersections of setting goals, devising plans, and executing act…
arXiv:2603.27490v1 Announce Type: new
Abstract: As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods …
arXiv:2603.26718v1 Announce Type: cross
Abstract: We analyze the challenges of benchmarking scientific (multi)-agentic systems, including the difficulty of distinguishing reasoning from retrieval, the risks of data/model contamination, the lack of rel…
arXiv:2603.28488v1 Announce Type: new
Abstract: Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augmented generation (RAG) and multi-agent debate (MAD) addr…
arXiv:2603.26542v2 Announce Type: replace-cross
Abstract: Buffer zones are essential in production systems to decouple sequential processes. In dense floor storage environments, such as space-constrained brownfield facilities, manual operation is incr…
arXiv:2603.26710v1 Announce Type: cross
Abstract: In this work, we present a modular and interpretable framework that uses Large Language Models (LLMs) to automate candidate assessment in recruitment. The system integrates diverse sources, including j…
arXiv:2603.27306v1 Announce Type: cross
Abstract: Large language models (LLMs) have been proposed as supervisory agents for spacecraft operations, but existing approaches rely on static prompting and do not improve across repeated executions. We intro…
arXiv:2509.15219v2 Announce Type: replace
Abstract: Trajectory prediction is a fundamental problem in computer vision, vision-language-action models, world models, and autonomous systems, with broad impact on autonomous driving, robotics, and surveill…
arXiv:2603.25821v1 Announce Type: new
Abstract: We present Doctorina MedBench, a comprehensive evaluation framework for agent-based medical AI based on the simulation of realistic physician-patient interactions. Unlike traditional medical benchmarks t…