paper-with-me

홈 › Papers

REVERE: Reflective Evolving Research Engineer for Scientific Workflows

2026-03-21 · Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan arxiv

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured merges, resulting in knowledge loss. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories, underspecified environments, and weak feedback, where reproducing results from public codebases is an established evaluation regime. We introduce Reflective Evolving Research Engineer (REVERE), a framework that continuously learns from Global Training Context, recognizes recurring failure modes in cross-repository execution trajectories, distills them into reusable heuristics, and performs targeted edits across three configurable fields: the system prompt, a task-prompt template, and a cumulative cheatsheet. REVERE, via this reflective optimization framework, improves performance over prior state-of-the-art expert-crafted instructions on research coding tasks by 4.50% on SUPER, 3.51% on ResearchCodeBench, and 4.89% on ScienceAgentBench across their respective metrics. These results demonstrate that agents equipped with mechanisms for continual learning and global memory consolidation can meaningfully evolve their capabilities over time.

📄 PDF Abstract BibTeX arXiv:2603.20667

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

2026-04-19 · Xinyu Zhu, Yuzhu Cai, Zexi Liu, Cheng Wang 외 arxiv

The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly stati…

Self-evolving Agents with reflective and memory-augmented abilities

2024-09-01 · Xuechen Liang, Yangfan He, Yinghui Xia, Xinyuan Song 외

Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making. In this research, we propose a novel framework b…

Decision Making

MARS: Modular Agent with Reflective Search for Automated AI Research

2026-02-02 · Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam, Rui Meng 외 arxiv

A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model…

EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

2026-03-09 · Yougang Lyu, Xi Zhang, Xinhao Yi, Yuyue Zhao 외 arxiv

The increasing adoption of Large Language Models (LLMs) has enabled AI scientists to perform complex end-to-end scientific discovery tasks requiring coordination of specialized roles, including idea generation and experi…

Code Search

HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research

2025-08-04 · Yinghao Zhu, Yifan Qi, Zixiang Wang, Lei Gu 외 arxiv

The rapid proliferation of scientific knowledge presents a grand challenge: transforming this vast repository of information into an active engine for discovery, especially in high-stakes domains like healthcare. Current…