FrogNano: Training a 4B Coding Agent via Online Task Synthesis

• URL: http://arxiv.org/abs/2609.07925v3
• Date: Mon, 14 Sep 2026 16:12:24 GMT
• Title: FrogNano: Training a 4B Coding Agent via Online Task Synthesis
• Abstract summary: FrogNano is a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively.<n>It is post-trained exclusively via RL on around 1,500 SWE environments with synthetic tasks.
• Score: 61.25325155871018
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present FrogNano, a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively, even under resource-constrained environments. It is post-trained exclusively via RL on around 1,500 SWE environments with synthetic tasks. A key ingredient for improving performance is an online task synthesis pipeline that creates tasks calibrated to the frontier of learnability for the current checkpoint. This report provides evidence that competitive small coding agents can be trained with synthetic tasks alone, without traditional distillation from larger models, and that generating tasks at the learnability frontier of the current agent is important. We report details on the training methodology, evaluations across diverse environments, and in-depth analyses, serving as a foundation for our ongoing exploration of lightweight yet capable coding agents that can run on minimal hardware.

Related papers

• SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL [38.05711358650287]
  Computer use agents (CUAs) are emerging as a powerful interface for automating complex digital through visual perception and GUI execution.<n>Online reinforcement learning with verifiable rewards (RLVR) has emerged as a key direction for scaling their capabilities.<n>We introduce ScaleCUA, a unified framework that scales online RL for CUAs via verifiable task synthesis and efficient training.
  arXiv  Detail & Related papers  (2026-07-13T07:32:35Z)
• AI Scientist via Synthetic Task Scaling [2.056976961583532]
  We provide a novel synthetic environment generation pipeline targeting machine learning agents.<n>Our pipeline automatically synthesizes machine learning challenges compatible with the SWE-agent framework.<n>We tackle MLGym, a benchmark for machine learning tasks.
  arXiv  Detail & Related papers  (2026-03-17T23:43:16Z)
• SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding [41.98672557723593]
  We introduce SWEQA-Pro, a benchmark constructed from diverse, long-tail repositories with executable environments.<n>We also propose a scalable synthetic data pipeline that powers a two-stage training recipe: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning from AI Feedback (RLAIF)<n> Empirically, a Qwen3-8B model trained with our recipe surpasses GPT-4o by 2.3 points on SWE-QA-Pro and substantially narrows the gap to state-of-the-art models.
  arXiv  Detail & Related papers  (2026-03-17T05:12:48Z)
• KARL: Knowledge Agents via Reinforcement Learning [63.627906947205624]
  We present a system for training enterprise search agents via reinforcement learning.<n> KARLBench is a multi-capability evaluation suite spanning six distinct search regimes.<n>We show that models trained across heterogeneous search behaviors generalize substantially better than those optimized for any single benchmark.
  arXiv  Detail & Related papers  (2026-03-05T14:30:25Z)
• Hybrid-Gym: Training Coding Agents to Generalize Across Tasks [59.95803522351185]
  In this paper, we describe some transferable skills that are shared across diverse tasks.<n>We propose a training environment, Hybrid-Gym, consisting of a set of scalable synthetic tasks.<n>Experiments show that agents trained on our synthetic tasks effectively generalize diverse real-world tasks.
  arXiv  Detail & Related papers  (2026-02-18T19:30:55Z)
• Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning [62.499592503950026]
  Large language model (LLM) have empowered autonomous agents to perform complex tasks that require multi-turn interactions with tools and environments.<n>We propose Agent World Model (AWM), a fully synthetic environment generation pipeline.<n>We scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets.
  arXiv  Detail & Related papers  (2026-02-10T18:55:41Z)
• InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling [71.37579508777843]
  Large language models (LLMs) have revolutionized artificial intelligence by enabling complex reasoning capabilities.<n>To address this gap, we present InternBootcamp, an open-source framework comprising 1000+ domain-diverse task environments.
  arXiv  Detail & Related papers  (2025-08-12T05:00:00Z)
• Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments [33.83610929282721]
  Learn-by-interact is a data-centric framework to adapt large language models (LLMs) to any given environments without human annotations.<n>We assess the quality of our synthetic data by using them in both training-based scenarios and training-free in-context learning (ICL)<n>Experiments on SWE-bench, WebArena, OSWorld and Spider2-V spanning across realistic coding, web, and desktop environments show the effectiveness of Learn-by-interact.
  arXiv  Detail & Related papers  (2025-01-18T22:34:41Z)
• Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents [9.529492371336286]
  Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. We propose a novel approach, called Logical Specifications-guided Dynamic Task Sampling (LSTS) LSTS learns a set of RL policies to guide an agent from an initial state to a goal state based on a high-level task specification.
  arXiv  Detail & Related papers  (2024-02-06T04:00:21Z)
• Environment Generation for Zero-Shot Compositional Reinforcement Learning [105.35258025210862]
  Compositional Design of Environments (CoDE) trains a Generator agent to automatically build a series of compositional tasks tailored to the agent's current skill level. We learn to generate environments composed of multiple pages or rooms, and train RL agents capable of completing wide-range of complex tasks in those environments. CoDE yields 4x higher success rate than the strongest baseline, and demonstrates strong performance of real websites learned on 3500 primitive tasks.
  arXiv  Detail & Related papers  (2022-01-21T21:35:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.