arXiv AI By Prateek Kumar Sikdar

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

Read the original on arXiv AI →

arXiv:2606. 01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) and open-ended planning/reasoning steps (long, complex, high perplexity).

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning
Aug 12

MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale

arXiv:2608. 10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction.

By Yuhang Yao, Zeyu Wang, Wanyi Chen, Tongyun Yang, Yuhang Han, Jie Xiao, Chengke Bao, Tianyi Zhao, Lynn Ai, Eric Yang, Tianyu Shi