← Back to all news
arXiv AI By Shen Liu, Ze Zhou, Zhenguo Xu, Shaopu Wang, Yike Gao, Chunlei Wang

LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents

Read the original on arXiv AI →

LeafSkill introduces an external reuse layer for recursive LLM agents that retrieves semantically related action grounding experiences, binds action templates to current objects, and uses a lightweight 1.7B selector to choose or defer actions. This approach preserves high coverage of candidate actions under paraphrases (96–97%) and achieves a 97.34% adoption rate of unseen skill types. In experiments on Robotouille tasks, LeafSkill outperforms ReCAP, completing more tasks and reducing token usage and calls by over 14%.

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.

Related stories

Hugging Face Trending Papers
Aug 17

HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents

Long-horizon embodied tasks require LLM agents to iteratively decompose high-level goals, revise plans in response to environmental feedback, and ground leaf-level subgoals into valid executable actions. Recursive context-management methods such as ReCAP improve planning stability through multi-level task decomposition and parent-node refinement, but still repeatedly invoke the LLM at leaf nodes to ground atomic subtasks into exact valid actions.

llmsagentsrobotics
More like this →
arXiv AI
Sep 25

The Fellowship of the Query: Learning Retrieval Actions

The paper investigates how trajectory fine‑tuning can enhance small language models (SLMs) as next‑action controllers in retrieval‑augmented question answering. By building a seven‑way action‑prediction task from teacher search traces, the authors fine‑tune SLMs and cross‑lingual SLMs (xSLMs) using LoRA and evaluate on 1,646 held‑out examples, achieving a macro‑F1 of 0.6536 with Granite 4.1 3B. In an end‑to‑end controller/generator swap experiment on 149 trajectories, the fine‑tuned model improves Exact Match from 0.7530 to 0.7946 and token F1 from 0.7783 to 0.8295, demonstrating that trajectory supervision boosts action prediction and evidence‑recording behavior.

By Mohammed Al-Maamari, Saber Zerhoudi, Michael Granitzer, Jelena Mitrovi\'c
llmsragagentsnlpfine-tuning
More like this →