arXiv Artificial IntelligenceReasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning
arXiv:2602.00994v3 Announce Type: replace Abstract: Agentic Reinforcement Learning (ARL) trains large…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2602.00994v3 Announce Type: replace Abstract: Agentic Reinforcement Learning (ARL) trains large…
arXiv Artificial IntelligencearXiv:2602.00685v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as…
arXiv Artificial IntelligencearXiv:2601.22118v3 Announce Type: replace Abstract: Artificial Intelligence (AI) has been on the rise in many…
arXiv Artificial IntelligencearXiv:2601.21545v2 Announce Type: replace Abstract: Agentic systems accumulate persistent memory across…
arXiv Artificial IntelligencearXiv:2601.15436v3 Announce Type: replace Abstract: We propose a novel perspective for probing LLM sycophancy…
arXiv Artificial IntelligencearXiv:2601.13206v2 Announce Type: replace Abstract: Large Language Models (LLMs) generate text token-by-token…
arXiv Artificial IntelligencearXiv:2601.05107v2 Announce Type: replace Abstract: As LLM-based agents are increasingly used in long-term…
arXiv Artificial IntelligencearXiv:2601.04035v2 Announce Type: replace Abstract: Mobile GUI agents have shown strong potential in…
arXiv Artificial IntelligencearXiv:2509.24711v4 Announce Type: replace Abstract: Current answering paradigms for Large Reasoning Models…
arXiv Artificial IntelligencearXiv:2509.23263v3 Announce Type: replace Abstract: Long-horizon GUI automation remains challenging due to…
arXiv Artificial IntelligencearXiv:2509.21054v3 Announce Type: replace Abstract: Understanding persuasion is critical for the safety and…
arXiv Artificial IntelligencearXiv:2509.18123v2 Announce Type: replace Abstract: Accurate interpretation of soil moisture patterns is…