swe-rm-verifier

Improve SWE agent RL via execution-free reward models optimized for three metrics beyond TTS: discriminative ability (AUC) and calibration (ECE). Shows TTS alone insufficient—models must distinguish correct/incorrect trajectories and align confidence with actual correctness—improving SWE-Bench Verified by 7-10 points with 30B MoE verifier.

跳到安装

仓库: ADu2021/skillXiv
最近来源活动: 2026年3月24日 19:42
检测到的 SKILL.md 语言: 英语
星标: 6
分支: 0

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/ADu2021/skillXiv --skill swe-rm-verifier

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

SKILL.md

来源说明 · 只读预览

返回搜索返回安装

meaningful-kebab-case-name

Convert arXiv papers into ready-to-use agent skills using category-aware extraction. First classifies the paper into one or more of 11 research categories, then applies a specialized extraction pipeline for each category — because different types of papers produce different types of usable knowledge. A single paper can yield multiple skills if it spans categories. Use this skill whenever the user wants to turn a paper into a skill, extract practical techniques from research, build a skill library from papers, convert arXiv papers into reusable agent instructions, or batch-process multiple papers into skills. Also trigger when someone asks about extracting actionable knowledge from papers, making research practical for LLM agents, or systematically converting academic contributions into structured agent capabilities.

2026-03-26

action-quantization-behavior-cloning

Establish regret bounds for behavior cloning with discretized actions combining statistical error and quantization error terms. Prove smoothness requirements for safe quantizer design, show that learning-based quantizers fail these requirements, and propose model-based augmentation to reduce error dependence from H² to H.

2026-03-26

adaptive-lora-personalized-ranks

Dynamically allocate LoRA ranks per-layer during fine-tuning instead of using fixed uniform ranks. Learn optimal rank for each layer and subject via variational framework with discretized exponential distribution, reducing memory footprint while maintaining fidelity and text-alignment.

2026-03-26

查看这个仓库的全部 Skills

name	swe-rm-verifier
title	SWE-RM: Execution-Free Feedback for SWE Agents
version	0.0.2
engine	skillxiv-v0.0.2-claude-opus-4.6
license	MIT
url	https://arxiv.org/abs/2512.21919
keywords	["reward-model","software-engineering","reinforcement-learning","verification"]
description	Improve SWE agent RL via execution-free reward models optimized for three metrics beyond TTS: discriminative ability (AUC) and calibration (ECE). Shows TTS alone insufficient—models must distinguish correct/incorrect trajectories and align confidence with actual correctness—improving SWE-Bench Verified by 7-10 points with 30B MoE verifier.

Overview

SWE-RM shows that reward model evaluation requires three complementary metrics.

Core Technique

Three-Metric Evaluation:

# Not just TTS (top-1 ranking)
tts_score = rank_best_solution_first(predictions)

# Also discriminative ability
auc_score = compute_auc(correct_vs_incorrect)

# And calibration
ece_score = expected_calibration_error(confidence, accuracy)

When to Use

Use when: SWE agent training, RL reward modeling, importance of calibration.

References

Discriminative ability vs ranking metrics
Calibration error measurement
Multi-objective reward model design

swe-rm-verifier

来源信息

安装方式

检查来源文件

同仓库更多 Skills

同仓库更多 Skills

Overview

Core Technique

When to Use

References

Overview

Core Technique

When to Use

References