arXiv:2606. 10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes.
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.
arXiv:2607. 28609v2 Announce Type: replace Abstract: Computer-using agents (CUAs) are advancing rapidly across the digital world.
arXiv:2606. 12674v1 Announce Type: new Abstract: Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents.
arXiv:2606. 03892v1 Announce Type: cross Abstract: Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns.
arXiv:2608. 00106v1 Announce Type: new Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it.
The paper introduces VHD-Play, a pipeline that first samples and solves a mathematical model before generating agentic reinforcement learning environments, ensuring that dynamics and evaluation are aligned from the outset. This approach yields 3,300 diverse environments at a low cost and significantly improves the performance of a large language‑model agent (Qwen3.6‑35B‑A3B) across multiple diagnostic families and external benchmarks. The study demonstrates that stateful interaction is a key factor in learning gains and that scaling the training substrate can further enhance performance.
arXiv:2607. 05471v1 Announce Type: cross Abstract: We present KAT-Coder-V2.