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

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

URL: http://arxiv.org/abs/2512.03549v1
Date: Wed, 03 Dec 2025 08:15:10 GMT
Title: PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks
Authors: Yuki Orimo, Iori Kurata, Hodaka Mori, Ryuhei Okuno, Ryohto Sawada, Daisuke Okanohara,
Abstract summary: We introduce PARC, a coding agent for the autonomous execution of long-horizon computational tasks.<n>We evaluate PARC across computational science and data science tasks.<n>Results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback.
Score: 0.0
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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.

Related papers

QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities [0.7519872646378835]
QUASAR is a universal autonomous system for atomistic simulation designed to facilitate production-grade scientific discovery.<n>We benchmark QUASAR against a series of three-tiered tasks, progressing from routine tasks to frontier research challenges such as photocatalyst screening and novel material assessment.<n>Results suggest that QUASAR can function as a general atomistic reasoning system rather than a task-specific automation framework.
arXiv Detail & Related papers (2026-01-30T05:29:44Z)
Towards Agentic Intelligence for Materials Science [73.4576385477731]
This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining to goal-conditioned agents interfacing with simulation and experimental platforms.<n>To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science.
arXiv Detail & Related papers (2026-01-29T23:48:43Z)
An Agentic Framework for Autonomous Materials Computation [70.24472585135929]
Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery.<n>Recent advances integrate LLMs into agentic frameworks, enabling retrieval, reasoning, and tool use for complex scientific experiments.<n>Here, we present a domain-specialized agent designed for reliable automation of first-principles materials computations.
arXiv Detail & Related papers (2025-12-22T15:03:57Z)
SelfAI: Building a Self-Training AI System with LLM Agents [79.10991818561907]
SelfAI is a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations.<n>An Experiment Manager orchestrates parallel, fault-tolerant training across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback.<n>Across regression, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials.
arXiv Detail & Related papers (2025-11-29T09:18:39Z)
LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering [90.84806758077536]
We introduce textbfLoCoBench-Agent, a comprehensive evaluation framework specifically designed to assess large language models (LLMs) agents in realistic, long-context software engineering.<n>Our framework extends LoCoBench's 8,000 scenarios into interactive agent environments, enabling systematic evaluation of multi-turn conversations.<n>Our framework provides agents with 8 specialized tools (file operations, search, code analysis) and evaluates them across context lengths ranging from 10K to 1M tokens.
arXiv Detail & Related papers (2025-11-17T23:57:24Z)
ParaCook: On Time-Efficient Planning for Multi-Agent Systems [62.471032881396496]
Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks.<n>We present ParaCook, a benchmark for time-efficient collaborative planning.
arXiv Detail & Related papers (2025-10-13T16:47:07Z)
AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation [0.10999592665107412]
AutoLabs is a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols.<n>We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity.<n>Our results demonstrate that agent reasoning capacity is the most critical factor for success.
arXiv Detail & Related papers (2025-09-30T01:51:46Z)
Reinforcement Learning Foundations for Deep Research Systems: A Survey [31.57262766437479]
This survey is the first dedicated to the RL foundations of deep research systems.<n>It systematizes recent work along three axes: (i) data synthesis and curation; (ii) RL methods for agentic research covering stability, sample efficiency, long context handling, reward and credit design, multi-objective optimization, and multimodal integration.<n>We distill recurring patterns, surface infrastructure bottlenecks, and offer practical guidance for training robust, transparent deep research agents with RL.
arXiv Detail & Related papers (2025-09-08T14:27:23Z)
Benchmarking LLM-based Agents for Single-cell Omics Analysis [6.915378212190715]
AI agents offer a paradigm shift, enabling adaptive planning, executable code generation, traceable decisions, and real-time knowledge fusion.<n>We introduce a novel benchmarking evaluation system to rigorously assess agent capabilities in single-cell omics analysis.
arXiv Detail & Related papers (2025-08-16T04:26:18Z)
Deep Research Agents: A Systematic Examination And Roadmap [109.53237992384872]
Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
arXiv Detail & Related papers (2025-06-22T16:52:48Z)
Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents [61.36681529571202]
We describe a new concept for reproducible robotics research that integrates development and benchmarking. One of the central components of this setup is the Duckietown Autolab, a standardized setup that is itself relatively low-cost and reproducible. We validate the system by analyzing the repeatability of experiments conducted using the infrastructure and show that there is low variance across different robot hardware and across different remote labs.
arXiv Detail & Related papers (2020-09-09T15:31:29Z)

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