Papers
arxiv:2603.20667

REVERE: Reflective Evolving Research Engineer for Scientific Workflows

Published on Mar 21
· Submitted by
Aniketh
on Mar 24
Authors:
,
,

Abstract

REVERE is a framework that enhances research coding agent performance through reflective optimization, global context learning, and cumulative knowledge consolidation across multiple task domains.

AI-generated summary

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.

Community

Paper submitter

Self-adapting Research Engineer with Global Memory and iterative learning, beating strong baselines on SUPER-Bench, ResearchCodeBench and ScienceAgentBench, through evolving prompt and context updates

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2603.20667 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2603.20667 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.20667 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.