Cover Image

Composing Policy Gradients and Prompt Optimization for Language Model Programs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ziems, Noah, Soylu, Dilara, Agrawal, Lakshya A, Miller, Isaac, Lai, Liheng, Qian, Chen, Song, Kaiqiang, Jiang, Meng, Klein, Dan, Zaharia, Matei, D'Oosterlinck, Karel, Potts, Christopher, Khattab, Omar
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together
by: Soylu, Dilara, et al.
Published: (2024)

In-Context Learning for Extreme Multi-Label Classification
by: D'Oosterlinck, Karel, et al.
Published: (2024)

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
by: Agrawal, Lakshya A, et al.
Published: (2025)

LangProBe: a Language Programs Benchmark
by: Tan, Shangyin, et al.
Published: (2025)

ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
by: Saad-Falcon, Jon, et al.
Published: (2023)

Updating CLIP to Prefer Descriptions Over Captions
by: Zur, Amir, et al.
Published: (2024)

WARP: An Efficient Engine for Multi-Vector Retrieval
by: Scheerer, Jan Luca, et al.
Published: (2025)

Building Efficient and Effective OpenQA Systems for Low-Resource Languages
by: Budur, Emrah, et al.
Published: (2024)

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
by: Singhvi, Arnav, et al.
Published: (2023)

Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
by: D'Oosterlinck, Karel, et al.
Published: (2024)

Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
by: Opsahl-Ong, Krista, et al.
Published: (2024)

Drowning in Documents: Consequences of Scaling Reranker Inference
by: Jacob, Mathew, et al.
Published: (2024)

optimize_anything: A Universal API for Optimizing any Text Parameter
by: Agrawal, Lakshya A, et al.
Published: (2026)

GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data Generation
by: Elmaaroufi, Karim, et al.
Published: (2025)

Image and Data Mining in Reticular Chemistry Using GPT-4V
by: Zheng, Zhiling, et al.
Published: (2023)

Learning, Fast and Slow: Towards LLMs That Adapt Continually
by: Tiwari, Rishabh, et al.
Published: (2026)

ColBERT-serve: Efficient Multi-Stage Memory-Mapped Scoring
by: Huang, Kaili, et al.
Published: (2025)

Why Do Multi-Agent LLM Systems Fail?
by: Cemri, Mert, et al.
Published: (2025)

SIEVE: Sample-Efficient Parametric Learning from Natural Language
by: Asawa, Parth, et al.
Published: (2026)

TOWER: Tree Organized Weighting for Evaluating Complex Instructions
by: Ziems, Noah, et al.
Published: (2024)

Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
by: Morrison, Jacob, et al.
Published: (2026)

ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data
by: Patel, Liana, et al.
Published: (2024)

World Model on Million-Length Video And Language With Blockwise RingAttention
by: Liu, Hao, et al.
Published: (2024)

Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines
by: Arabzadeh, Negar, et al.
Published: (2026)

RAG over Thinking Traces Can Improve Reasoning Tasks
by: Arabzadeh, Negar, et al.
Published: (2026)

Querying Databases with Function Calling
by: Shorten, Connor, et al.
Published: (2025)

Optimizing Decomposition for Optimal Claim Verification
by: Lu, Yining, et al.
Published: (2025)

Determination of the General Attitude to and Anxiety About Artificial Intelligence of Nurses Working in Internal Medicine Clinics: A Mixed‐Method Study
by: Ahmet Seven, et al.
Published: (2025)

Organ Transplantation Readiness Scale: A Scale Development Study
by: Dilek Soylu, et al.
Published: (2025)

Long Context RAG Performance of Large Language Models
by: Leng, Quinn, et al.
Published: (2024)

Ecosystem Graphs: The Social Footprint of Foundation Models
by: Bommasani, Rishi, et al.
Published: (2023)

ChatGPT in the classroom. Exploring its potential and limitations in a Functional Programming course
by: Popovici, Dan-Matei
Published: (2024)

Backtracing: Retrieving the Cause of the Query
by: Wang, Rose E., et al.
Published: (2024)

Predicting and Optimizing Nanomaterial Synthesis Outcomes While Modelling Defects Using AI and ML
by: Jaiswal, Lakshya
Published: (2025)

A Geometric Solution to the Isoperimetric Problem and its Quantitative Inequalities
by: Chaudhary, Lakshya
Published: (2025)

Discovering T-Dualities of Little String Theories
by: Bhardwaj, Lakshya
Published: (2022)

vCache: Verified Semantic Prompt Caching
by: Schroeder, Luis Gaspar, et al.
Published: (2025)

Vector Policy Optimization: Training for Diversity Improves Test-Time Search
by: Bahlous-Boldi, Ryan, et al.
Published: (2026)

Prompts as Auto-Optimized Training Hyperparameters: Training Best-in-Class IR Models from Scratch with 10 Gold Labels
by: Xian, Jasper, et al.
Published: (2024)