arXiv Artificial IntelligenceHaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents
arXiv:2608.16447v2 Announce Type: replace Abstract: Long-horizon embodied tasks require LLM agents to…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2608.16447v2 Announce Type: replace Abstract: Long-horizon embodied tasks require LLM agents to…
arXiv Artificial IntelligencearXiv:2608.15592v2 Announce Type: replace Abstract: Efficient LLM serving is often bottlenecked by the need…
arXiv Artificial IntelligencearXiv:2608.15454v2 Announce Type: replace Abstract: Byte-level hierarchical language models (LMs) have…
arXiv Artificial IntelligencearXiv:2608.15389v2 Announce Type: replace Abstract: LLM-based Text-to-SQL progress is reported across…
arXiv Artificial IntelligencearXiv:2608.15382v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly proposed…
arXiv Artificial IntelligencearXiv:2606.28455v3 Announce Type: replace-cross Abstract: World models can predict future physical states…
arXiv Artificial IntelligencearXiv:2608.14354v2 Announce Type: replace Abstract: Enabling LLM agents to sustain productive, stable, and…
arXiv Artificial IntelligencearXiv:2608.12750v2 Announce Type: replace-cross Abstract: LLM-based simulated clients are increasingly used…
arXiv Artificial IntelligencearXiv:2608.12645v2 Announce Type: replace Abstract: LLM judges have become central infrastructure for model…
arXiv Artificial IntelligencearXiv:2505.18315v4 Announce Type: replace-cross Abstract: We introduce CoLoRA (Convolutional Low-Rank…
arXiv Artificial IntelligencearXiv:2608.11234v2 Announce Type: replace Abstract: Managing modern computing infrastructure has become a…
arXiv Artificial IntelligencearXiv:2608.10983v2 Announce Type: replace-cross Abstract: Multi-modal recommenders fuse user-item interaction…