Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2607. 15263v1 Announce Type: cross Abstract: Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion.
arXiv:2607. 14386v1 Announce Type: new Abstract: Data science tasks span from closed-ended information extraction to open-ended analysis, presenting significant challenges for automation.
arXiv:2509. 00761v4 Announce Type: replace Abstract: Large language models are increasingly deployed for legal question answering, where evaluations typically focus on multiple-choice accuracy.
arXiv:2607. 14541v1 Announce Type: new Abstract: Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads.
arXiv:2607. 13501v2 Announce Type: replace Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions.
arXiv:2607. 14582v1 Announce Type: new Abstract: Existing LLM-based theorem provers have achieved impressive results on formal mathematics benchmarks, yet they remain confined to acting as autonomous agents that prove a stated proposition.
arXiv:2607. 14178v1 Announce Type: new Abstract: Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research systems remain predominantly focused on empirically driven domains with quantitative benchmarks, leaving theory-driven discovery, particularly in mathematically grounded disciplines requiring rigorous proofs and synthesis of domain knowledge, largely underexplored.
arXiv:2607. 14675v1 Announce Type: cross Abstract: Robust human-robot interaction in complex environments requires accurate gesture perception, semantic scene understanding, and reliable task planning under limited onboard computing resources.
arXiv:2607. 14145v1 Announce Type: new Abstract: Tool-augmented large language model agents excel at long-horizon tasks, yet they are typically post-trained on fixed toolsets.
arXiv:2607. 14138v1 Announce Type: cross Abstract: The most prevalent distributed systems today include people and their personal machines (smartphones).
arXiv:2607. 14573v1 Announce Type: new Abstract: Payment integration is a demanding repository-level software task: agents must select a suitable product, implement coordinated client-server flows, verify payment outcomes, and preserve consistency between transaction and business states.
arXiv:2607. 15001v1 Announce Type: cross Abstract: Lattice quantum chromodynamics (LQCD) provides a first-principles framework for computing hadronic observables, but its practical use remains limited by the substantial expertise required to turn research motivation into reliable computing workflows.
arXiv:2607. 06214v2 Announce Type: replace Abstract: This paper offers a framework for considering curiosity as an ecosystem.
arXiv:2607. 14952v1 Announce Type: new Abstract: A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment.
How to define recurring work, give AI the right context, explain what high-quality work looks like, and decide where human judgment is still needed. The post Prepare These 5 Assets Before Your AI Agents Take On More Work appeared first on Towards Data Science .
RoboCup has always been a scenario to develop systems that solve real-world problems. Driven by the main goal of playing against the 2050 FIFA World Cup champions, the RoboCup Soccer leagues need to constantly measure how the research community is progressing.
Cross-modal learning, i. e.
arXiv:2607. 13080v1 Announce Type: cross Abstract: Autonomous coding agents force engineering organizations to choose between API-based frontier models -- strong reasoning at high token cost -- and on-premise quantized open-weights models, which promise low-marginal-cost scaling and data sovereignty at some loss of reasoning fidelity.
arXiv:2607. 13189v1 Announce Type: cross Abstract: We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chinese).
arXiv:2607. 13078v1 Announce Type: cross Abstract: LLMs are now proposed for fraud detection, scam investigation, content moderation, and other trust-and-safety workflows.