by ODEFTO AI Labs
arXiv:2607.18970v3 Announce Type: replace-cross Abstract: Agent Skills have become persistent behavioral artifacts across independent AI agent systems. They combine natural-language…
arXiv:2608.20341v1 Announce Type: new Abstract: Frontier coding agents backed by large language models with context windows from hundreds of thousands…
arXiv:2608.11238v2 Announce Type: replace Abstract: Retrieval-augmented generation improves the factuality of large language models by grounding responses in retrieved evidence,…
arXiv:2608.19885v2 Announce Type: replace-cross Abstract: After the inputs X are known, how much additional information does the label Y carry…
arXiv:2608.20757v1 Announce Type: cross Abstract: We describe the PSK submission to the WMT 2026 Multilingual Instruction Shared Task. Our system…
arXiv:2608.18087v2 Announce Type: replace-cross Abstract: Existing subword tokenizers optimize statistical compression but ignore morphological structure, particularly the relationship between roots…
arXiv:2608.19762v1 Announce Type: cross Abstract: A minibatch can influence training beyond the update at which it is observed because AdamW…
arXiv:2608.19776v1 Announce Type: cross Abstract: Current dexterous grasp planners primarily optimize for physical stability, focusing on whether an object can…
arXiv:2608.19085v2 Announce Type: replace-cross Abstract: Anticipating how scenes evolve under ego actions is fundamental to safe autonomous driving, yet the…
arXiv:2608.19202v1 Announce Type: new Abstract: Interactive AI agents must acquire the right context as efficiently as possible. When a user…