KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nadafian, Alireza, Mohammadshahi, Alireza, Yazdani, Majid
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912865986805760
author Nadafian, Alireza
Mohammadshahi, Alireza
Yazdani, Majid
author_facet Nadafian, Alireza
Mohammadshahi, Alireza
Yazdani, Majid
contents We introduce KAPSO, a modular framework for autonomous program synthesis and optimization. Given a natural language goal and an evaluation method, KAPSO iteratively performs ideation, code synthesis and editing, execution, evaluation, and learning to improve a runnable artifact toward measurable objectives. Rather than treating synthesis as the endpoint, KAPSO uses synthesis as an operator within a long-horizon optimization loop, where progress is defined by evaluator outcomes. KAPSO targets long-horizon failures common in coding agents, including lost experimental state, brittle debugging, and weak reuse of domain expertise, by integrating three tightly coupled components. First, a git-native experimentation engine isolates each attempt as a branch, producing reproducible artifacts and preserving provenance across iterations. Second, a knowledge system ingests heterogeneous sources, including repositories, internal playbooks, and curated external resources such as documentation, scientific papers, and web search results, and organizes them into a structured representation that supports retrieval over workflows, implementations, and environment constraints. Third, a cognitive memory layer coordinates retrieval and maintains an episodic store of reusable lessons distilled from experiment traces (run logs, diffs, and evaluator feedback), reducing repeated error modes and accelerating convergence. We evaluated KAPSO on MLE-Bench (Kaggle-style ML competitions) and ALE-Bench (AtCoder heuristic optimization), and report end-to-end performance. Code Available at: https://github.com/Leeroo-AI/kapso
format Preprint
id arxiv_https___arxiv_org_abs_2601_21526
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization
Nadafian, Alireza
Mohammadshahi, Alireza
Yazdani, Majid
Artificial Intelligence
Computation and Language
Software Engineering
We introduce KAPSO, a modular framework for autonomous program synthesis and optimization. Given a natural language goal and an evaluation method, KAPSO iteratively performs ideation, code synthesis and editing, execution, evaluation, and learning to improve a runnable artifact toward measurable objectives. Rather than treating synthesis as the endpoint, KAPSO uses synthesis as an operator within a long-horizon optimization loop, where progress is defined by evaluator outcomes. KAPSO targets long-horizon failures common in coding agents, including lost experimental state, brittle debugging, and weak reuse of domain expertise, by integrating three tightly coupled components. First, a git-native experimentation engine isolates each attempt as a branch, producing reproducible artifacts and preserving provenance across iterations. Second, a knowledge system ingests heterogeneous sources, including repositories, internal playbooks, and curated external resources such as documentation, scientific papers, and web search results, and organizes them into a structured representation that supports retrieval over workflows, implementations, and environment constraints. Third, a cognitive memory layer coordinates retrieval and maintains an episodic store of reusable lessons distilled from experiment traces (run logs, diffs, and evaluator feedback), reducing repeated error modes and accelerating convergence. We evaluated KAPSO on MLE-Bench (Kaggle-style ML competitions) and ALE-Bench (AtCoder heuristic optimization), and report end-to-end performance. Code Available at: https://github.com/Leeroo-AI/kapso
title KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization
topic Artificial Intelligence
Computation and Language
Software Engineering
url https://arxiv.org/abs/2601.21526