REVERE让代码研究代理自我进化，提升跨任务泛化能力。
REVERE: Reflective Evolving Research Engineer
- 通过全局上下文学习，提炼跨仓库失败模式为可复用规则。
- 在多个基准上比人工指令提升4.5%至4.89%，效率高出2.7倍。
- 适合需要长期迭代优化的研究型代码生成场景。
现有提示优化技术依赖局部信号，导致任务间泛化能力差；同时更新机制薄弱（如全量重写或无结构合并），引发知识丢失与适应不稳定。这些局限在异构仓库、弱反馈的研究编码流程中尤为突出，阻碍抽象与跨任务学习。我们提出轻量级自适应代理框架 REVERE，其从全局训练上下文中学习，将重复出现的跨仓库失败模式提炼为可复用启发式规则，并实施针对性代码级提示修改。REVERE 在长周期与单次样本基准上均验证有效，在 SUPER 上优于人工指令 4.50%，在 ResearchCodeBench 上提升 1.3%，在 ScienceAgentBench 上提升 4.89%。其成本仅为基线的十分之一，适应速度加快 2.7 倍，证明具备持续学习与全局记忆整合能力的自适应代理可实现能力的持续演化。
原文摘要 · Abstract (English)
Existing prompt-optimization techniques rely on local signals, causing poor generalization across tasks. In addition, they also rely on weak update mechanisms, such as full-prompt rewrites or unstructured merges, which cause knowledge loss and unstable adaptation. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories and weak feedback, limiting abstraction and learning across tasks. We introduce Reflective Evolving Research Engineer (REVERE), a lightweight, self-adapting agent framework that learns from a Global Training Context, distills recurring cross-repository failure modes into reusable heuristics, and applies targeted, code-based edits to agent prompts. REVERE is evaluated across settings ranging from long-horizon to single-shot benchmarks, and improves over prior expert-crafted instructions by 4.50% on SUPER, 1.3% on ResearchCodeBench, and 4.89% on ScienceAgentBench. It does so at nearly 10x lower cost and 2.7x faster adaptation than existing prompt-optimization baselines, demonstrating that self-adapting agents with continual learning and global memory consolidation can meaningfully evolve their capabilities over time.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。