# Ant Ling — Agentic Learning

- Company: Ant Ling (ant-ling.com)
- Announced: 2025-04-01
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://developer.ant-ling.com/en/blogs/agenticlearning
- Record: https://forck.live/items/22343-agentic-learning
- Subject: Ling / Ring / Ming
- License: MIT License

Ant Ling introduced AgenticLearning, an open-source agent training paradigm for multi-turn interactions with environments. The project includes two frameworks: RAG-R1 for deep search and reasoning via multi-query parallelism, and FunReason for enhancing function calling capabilities through automated data refinement and a Self-Refinement Multiscale Loss approach. FunReason achieves GPT-4o-comparable performance on BFCL and mitigates catastrophic forgetting on HumanEval and MBPP.

## Evidence

Verbatim from https://developer.ant-ling.com/en/blogs/agenticlearning:

> We introduce AgenticLearning , an open-source agent training paradigm designed to empower researchers to train and evaluate autonomous agents effectively.

---

Record: https://forck.live/items/22343-agentic-learning
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md