PulseAugur
中
实时 20:46:28
English(EN) Tsinghua Team Open-Sources VeriLoop Coder-E1: Evidence-Governed Spiral Drives Verifiable Recursive Self-Improvement for Repository-Level Code Repair

清华大学发布 VeriLoop Coder-E1 用于可验证的代码修复

作者 PulseAugur 编辑部 · [1 个来源] ·

清华大学的研究人员开源了 VeriLoop Coder-E1，这是一个用于可验证递归自改进以进行代码修复的模型。VeriLoop Coder-E1 基于 Qwen3.6-27B 架构构建，采用“基于证据的螺旋式”方法来增强其代码修复能力。该模型在 SWE-bench Verified、SWE-bench Pro、Terminal-Bench 2.0 和 DeepSWE 等多个基准测试中表现强劲，尤其是在采用窄域 PEFT 和 Self-Harness 技术时。 AI

影响 此次发布为自动化代码修复和自改进提供了一个新工具，有望提高软件开发效率。

排序理由 具有基准测试结果的代码修复模型开源发布。[lever_c_demoted from research: ic=1 ai=1.0]

在 Pandaily 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

清华大学发布 VeriLoop Coder-E1 用于可验证的代码修复

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
具有基准测试结果的代码修复模型开源发布。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product, paper
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
68 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Pandaily TIER_1 English(EN) · [email protected] (Pandaily) ·

    清华团队开源 VeriLoop Coder-E1：证据驱动的螺旋实现可验证的递归自改进以进行存储库级代码修复

    VeriLoop Coder-E1 based on Qwen3.6-27B achieves SWE-bench Verified 85.20, SWE-bench Pro 62.38, Terminal-Bench 2.0 76.40, and DeepSWE 33.63 with narrow-domain PEFT and Self-Harness.

相关实体

相关话题