Image de couverture de livre

Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ishibashi, Yoichi, Yano, Taro, Oyamada, Masafumi
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Effective Harness Engineering for Algorithm Discovery with Coding Agents
par: Ishibashi, Yoichi, et autres
Publié: (2026)

LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents
par: Yano, Taro, et autres
Publié: (2025)

Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning
par: Ishibashi, Yoichi, et autres
Publié: (2025)

Can a Crow Hatch a Falcon? Lineage Matters in Predicting Large Language Model Performance
par: Tamura, Takuya, et autres
Publié: (2025)

An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability
par: Yamauchi, Yusuke, et autres
Publié: (2025)

Knowledge Sanitization of Large Language Models
par: Ishibashi, Yoichi, et autres
Publié: (2023)

$M^3$ Scaling Law: Optimizing Multi-Epoch, Multi-Lingual, and Multi-Stage Training for Low-Resource Language Models
par: Akimoto, Kosuke, et autres
Publié: (2024)

Jellyfish: A Large Language Model for Data Preprocessing
par: Zhang, Haochen, et autres
Publié: (2023)

ItD: Large Language Models Can Teach Themselves Induction through Deduction
par: Sun, Wangtao, et autres
Publié: (2024)

Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling
par: Pathmanathan, Pankayaraj, et autres
Publié: (2025)

Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight Framework
par: Enomoto, Masafumi, et autres
Publié: (2026)

Read More, Think More: Revisiting Observation Reduction for Web Agents
par: Enomoto, Masafumi, et autres
Publié: (2026)

Context Quality Matters in Training Fusion-in-Decoder for Extractive Open-Domain Question Answering
par: Akimoto, Kosuke, et autres
Publié: (2024)

Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization
par: Ishibashi, Yoichi, et autres
Publié: (2024)

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
par: Wang, Qianli, et autres
Publié: (2026)

Looking Inward: Language Models Can Learn About Themselves by Introspection
par: Binder, Felix J, et autres
Publié: (2024)

LightPAL: Lightweight Passage Retrieval for Open Domain Multi-Document Summarization
par: Enomoto, Masafumi, et autres
Publié: (2024)

Large Language Models are Demonstration Pre-Selectors for Themselves
par: Jin, Jiarui, et autres
Publié: (2025)

Can Language Models Critique Themselves? Investigating Self-Feedback for Retrieval Augmented Generation at BioASQ 2025
par: Ateia, Samy, et autres
Publié: (2025)

Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
par: Yong, Zheng-Xin, et autres
Publié: (2025)

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
par: Tie, Guiyao, et autres
Publié: (2025)

Can LLMs Explain Themselves Counterfactually?
par: Dehghanighobadi, Zahra, et autres
Publié: (2025)

DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability
par: He, Yunzhen, et autres
Publié: (2025)

Latent Principle Discovery for Language Model Self-Improvement
par: Ramji, Keshav, et autres
Publié: (2025)

AlphaResearch: Accelerating New Algorithm Discovery with Language Models
par: Yu, Zhaojian, et autres
Publié: (2025)

Large Language Models are Algorithmically Blind
par: Venkatesh, Sohan, et autres
Publié: (2026)

Large Language Models Can Self-Improve in Long-context Reasoning
par: Li, Siheng, et autres
Publié: (2024)

Importance Weighting Can Help Large Language Models Self-Improve
par: Jiang, Chunyang, et autres
Publié: (2024)

Self-Improvement in Multimodal Large Language Models: A Survey
par: Deng, Shijian, et autres
Publié: (2025)

Enabling Language Models to Implicitly Learn Self-Improvement
par: Wang, Ziqi, et autres
Publié: (2023)

Test-time Recursive Thinking: Self-Improvement without External Feedback
par: Zhuang, Yufan, et autres
Publié: (2026)

Helping Large Language Models Protect Themselves: An Enhanced Filtering and Summarization System
par: Muhaimin, Sheikh Samit, et autres
Publié: (2025)

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
par: Zelikman, Eric, et autres
Publié: (2024)

Structural Perturbation in Large Language Model Representations through Recursive Symbolic Regeneration
par: Eaglewood, Kathlyn, et autres
Publié: (2025)

LLMs Can Teach Themselves to Better Predict the Future
par: Turtel, Benjamin, et autres
Publié: (2025)

PRIME: Policy-Reinforced Iterative Multi-agent Execution for Algorithmic Reasoning in Large Language Models
par: Xu, Jiawei, et autres
Publié: (2026)

Advancing Large Language Model Attribution through Self-Improving
par: Huang, Lei, et autres
Publié: (2024)

Intrinsically Correct Algorithms and Recursive Coalgebras
par: Alexandru, Cass, et autres
Publié: (2025)

Recursive Introspection: Teaching Language Model Agents How to Self-Improve
par: Qu, Yuxiao, et autres
Publié: (2024)

Large Language Models Can Self-Improve At Web Agent Tasks
par: Patel, Ajay, et autres
Publié: (2024)