arXiv:2607. 00248v1 Announce Type: new Abstract: We present Seed2.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
We present Seed2. 0, a model series that takes a meaningful step toward solving complex, real-world tasks.
arXiv:2606. 14397v1 Announce Type: new Abstract: As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities.
InternBootcamp is an open‑source framework that offers over 1,000 domain‑diverse task environments for large language model (LLM) reasoning research. It introduces Bootcamp‑Eval, an automatically generated benchmark for comprehensive performance assessment. Experiments show that training on InternBootcamp significantly improves reasoning performance, with a 32B model achieving state‑of‑the‑art results on Bootcamp‑Eval and other established benchmarks, demonstrating that scaling the number of training tasks yields consistent gains.
arXiv:2606. 29929v1 Announce Type: new Abstract: Distilling historical trajectories into reusable experience to enhance future problem-solving has become a focal point of recent LLM research.
arXiv:2508.16821v2 Announce Type: replace Abstract: We introduce PuzzleJAX, a GPU-accelerated puzzle game engine and description language designed to support rapid benchmarking of tree search, reinfo...
arXiv:2609.14473v1 Announce Type: new Abstract: Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical...