Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks

About

We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work.

Yuki Orimo, Iori Kurata, Hodaka Mori, Ryuhei Okuno, Ryohto Sawada, Daisuke Okanohara• 2025

Related benchmarks

TaskDatasetResultRank
Polymer property predictionNeurIPS Open Polymer Prediction Challenge 2025 (public)
FFV R^20.825
4
Polytope Permutation Puzzle SolvingKaggle Santa The Polytope Permutation Puzzle 2023
Total Moves1.20e+6
4
Showing 2 of 2 rows

Other info

Follow for update