Image de couverture de livre

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wan, Xingchen, Zhou, Han, Sun, Ruoxi, Nakhost, Hootan, Jiang, Ke, Arık, Sercan Ö.
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
par: Wan, Xingchen, et autres
Publié: (2024)

Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration
par: Wan, Xingchen, et autres
Publié: (2025)

VISTA: A Test-Time Self-Improving Video Generation Agent
par: Long, Do Xuan, et autres
Publié: (2025)

SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)
par: Sun, Ruoxi, et autres
Publié: (2023)

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
par: Wang, Fei, et autres
Publié: (2024)

DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling
par: Wang, Fei, et autres
Publié: (2025)

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
par: Zhou, Han, et autres
Publié: (2025)

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL
par: Pourreza, Mohammadreza, et autres
Publié: (2025)

Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training
par: Chen, Maximillian, et autres
Publié: (2024)

Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling
par: Chen, Maximillian, et autres
Publié: (2024)

SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling
par: Chen, Jiefeng, et autres
Publié: (2025)

FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
par: Jalori, Gunjan, et autres
Publié: (2025)

Effective Large Language Model Adaptation for Improved Grounding and Citation Generation
par: Ye, Xi, et autres
Publié: (2023)

Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments
par: Su, Hongjin, et autres
Publié: (2025)

Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization
par: Lin, Xi, et autres
Publié: (2024)

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
par: Han, Sungwon, et autres
Publié: (2024)

SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging
par: Pourreza, Mohammadreza, et autres
Publié: (2024)

An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents
par: Jin, Bowen, et autres
Publié: (2025)

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
par: Pourreza, Mohammadreza, et autres
Publié: (2024)

Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations
par: Gu, Zhengyao, et autres
Publié: (2025)

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
par: Jin, Bowen, et autres
Publié: (2024)

Few-for-Many Personalized Federated Learning
par: Guo, Ping, et autres
Publié: (2026)

Mitigating Many-Shot Jailbreaking
par: Ackerman, Christopher M., et autres
Publié: (2025)

Many-Shot In-Context Learning
par: Agarwal, Rishabh, et autres
Publié: (2024)

Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey
par: Jain, Bhavuk, et autres
Publié: (2026)

Compressing Many-Shots in In-Context Learning
par: Khatri, Devvrit, et autres
Publié: (2025)

An Empirical Study of Many-to-Many Summarization with Large Language Models
par: Wang, Jiaan, et autres
Publié: (2025)

An Efficient Evolutionary Algorithm for Few-for-Many Optimization
par: Shang, Ke, et autres
Publié: (2026)

LANISTR: Multimodal Learning from Structured and Unstructured Data
par: Ebrahimi, Sayna, et autres
Publié: (2023)

Towards Compute-Optimal Many-Shot In-Context Learning
par: Golchin, Shahriar, et autres
Publié: (2025)

MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?
par: Yan, Kai, et autres
Publié: (2025)

Many-Shot In-Context Learning in Multimodal Foundation Models
par: Jiang, Yixing, et autres
Publié: (2024)

How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks
par: Arimbur, Johin Johny
Publié: (2026)

Many-Shot In-Context Learning for Molecular Inverse Design
par: Moayedpour, Saeed, et autres
Publié: (2024)

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
par: Parmar, Mihir, et autres
Publié: (2025)

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
par: Chen, Zihan, et autres
Publié: (2025)

LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
par: Jin, Bowen, et autres
Publié: (2025)

Focused Large Language Models are Stable Many-Shot Learners
par: Yuan, Peiwen, et autres
Publié: (2024)

Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization
par: Prasanna, Sai, et autres
Publié: (2024)

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
par: Chen, Kejia, et autres
Publié: (2026)