Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -7,10 +7,13 @@ date: 2025-07-25 17:42:32
paper_author: "UC Berkeley"
paper_doi: "10.48550/arXiv.2507.19457"
description: "GEPA는 실행 트레이스를 자연어로 성찰해 지시문을 고치고 파레토 프런티어로 후보를 고르는 프롬프트 옵티마이저입니다. Qwen3 8B 여섯 과제에서 최대 35배 적은 롤아웃으로 GRPO를 평균 6% 앞서며, 구조와 실험 결과를 정리합니다."
categories: ["Paper Reviews", "Finetuning"]
categories: ["Paper Reviews", "Language-Models"]
tags: ["Reflective-Prompt-Evolution", "Pareto-Based-Candidate-Selection", "Natural-Language-Reflection", "Prompt-Optimization", "Sample-Efficient-Optimization", "Reasoning-Models"]
cover: /assets/images/finetuning.jpg
cover: /assets/images/language-models.jpg
use_math: true
# First published under the Finetuning topic.
redirect_from:
- /paper-reviews/finetuning/2025/07/25/gepa-reflective-prompt-evolution-can-outperform-reinforcement-learning.html
---
## TL;DR

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -7,10 +7,13 @@ date: 2024-06-17 16:12:03
paper_author: "Stanford University"
paper_doi: "10.48550/arXiv.2406.11695"
description: "MIPRO는 다단계 LM 프로그램에서 모듈별 지시문과 시연 예시를 중간 레이블 없이 함께 최적화하는 DSPy 옵티마이저이며, Llama-3-8B를 쓴 일곱 과제 중 다섯에서 기준 옵티마이저를 앞섰습니다. 제안 전략, 크레딧 할당 방식, 실험 결과를 정리합니다."
categories: ["Paper Reviews", "Finetuning"]
categories: ["Paper Reviews", "Language-Models"]
tags: ["MIPRO-Optimizer", "Multi-Stage-LM-Programs", "Prompt-Optimization", "Bayesian-Surrogate-Model", "Instruction-Proposal", "Agentic-AI"]
cover: /assets/images/finetuning.jpg
cover: /assets/images/language-models.jpg
use_math: true
# First published under the Finetuning topic.
redirect_from:
- /paper-reviews/finetuning/2024/06/17/optimizing-instructions-and-demonstrations-for-multi-stage-language-model.html
---
## TL;DR

Expand Down
8 changes: 8 additions & 0 deletions script/published-urls.txt
Original file line number Diff line number Diff line change
Expand Up @@ -40,21 +40,26 @@
/paper-reviews/finetuning/2022/12/15/constitutional-ai-harmlessness-from-ai-feedback.html
/paper-reviews/finetuning/2023/05/23/qlora-efficient-finetuning-of-quantized-llms.html
/paper-reviews/finetuning/2023/05/29/direct-preference-optimization-your-language-model-is-secretly-a-reward-model.html
/paper-reviews/finetuning/2024/06/17/optimizing-instructions-and-demonstrations-for-multi-stage-language-model.html
/paper-reviews/finetuning/2025/07/25/gepa-reflective-prompt-evolution-can-outperform-reinforcement-learning.html
/paper-reviews/language-models/2023/02/27/llama-open-and-efficient-foundation-language-models.html
/paper-reviews/language-models/2023/07/18/llama-2-open-foundation-and-fine-tuned-chat-models.html
/paper-reviews/language-models/2023/10/05/dspy-compiling-declarative-language-model-calls-into-self-improving-pipelines.html
/paper-reviews/language-models/2023/10/10/mistral-7b.html
/paper-reviews/language-models/2024/01/05/deepseek-llm-scaling-open-source-language-models-with-longtermism.html
/paper-reviews/language-models/2024/01/08/mixtral-of-experts.html
/paper-reviews/language-models/2024/01/11/deepseekmoe-towards-ultimate-expert-specialization-in-mixture-of-experts-language-models.html
/paper-reviews/language-models/2024/01/25/deepseek-coder-when-the-large-language-model-meets-programming-the-rise-of-code-intelligence.html
/paper-reviews/language-models/2024/02/05/deepseekmath-pushing-the-limits-of-mathematical-reasoning-in-open-language-models.html
/paper-reviews/language-models/2024/05/07/deepseek-v2-a-strong-economical-and-efficient-mixture-of-experts-language-model.html
/paper-reviews/language-models/2024/06/17/optimizing-instructions-and-demonstrations-for-multi-stage-language-model.html
/paper-reviews/language-models/2024/07/31/gemma-2-improving-open-language-models-at-a-practical-size.html
/paper-reviews/language-models/2024/07/31/the-llama-3-herd-of-models.html
/paper-reviews/language-models/2024/11/22/tulu-3-pushing-frontiers-in-open-language-model-post-training.html
/paper-reviews/language-models/2024/12/27/deepseek-v3-technical-report.html
/paper-reviews/language-models/2025/01/22/deepseek-r1-incentivizing-reasoning-capability-in-llms-via-reinforcement-learning.html
/paper-reviews/language-models/2025/05/14/qwen3-technical-report.html
/paper-reviews/language-models/2025/07/25/gepa-reflective-prompt-evolution-can-outperform-reinforcement-learning.html
/paper-reviews/language-models/2025/07/28/kimi-k2-open-agentic-intelligence.html
/paper-reviews/language-models/2025/12/02/deepseek-v3.2-pushing-the-frontier-of-open-large-language-models.html
/paper-reviews/multimodal-learning/2023/12/19/gemini-a-family-of-highly-capable-multimodal-models.html
Expand All @@ -65,5 +70,8 @@
/paper-reviews/retrieval-augmented-generation/2024/04/24/from-local-to-global-a-graph-rag-approach-to-query-focused-summarization.html
/paper-reviews/retrieval-augmented-generation/2024/10/08/lightrag-simple-and-fast-retrieval-augmented-generation.html
/paper-reviews/retrieval-augmented-generation/2025/01/20/zep-a-temporal-knowledge-graph-architecture-for-agent-memory.html
/paper-summaries/agentic-ai/2023/05/23/rewoo-decoupling-reasoning-from-observations-for-efficient-augmented-language-summary.html
/paper-summaries/agentic-ai/2024/02/01/executable-code-actions-elicit-better-llm-agents-summary.html
/paper-summaries/agentic-ai/2025/11/26/toolorchestra-elevating-intelligence-via-efficient-model-and-tool-orchestration-summary.html
/paper-surveys/agentic-ai/2026/11/02/securing-llm-agents-from-prompt-injection-to-mcp-and-defenses.html
/tech-guides/agentic-ai/2026/10/23/strands-agents-sdk-the-agent-loop-hooks-and-production-controls.html