Cover Image

Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bensal, Shelly, Jamil, Umar, Bryant, Christopher, Russak, Melisa, Kamble, Kiran, Mozolevskyi, Dmytro, Ali, Muayad, AlShikh, Waseem
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

Expect the Unexpected: FailSafe Long Context QA for Finance
by: Kamble, Kiran, et al.
Published: (2025)

Writing in the Margins: Better Inference Pattern for Long Context Retrieval
by: Russak, Melisa, et al.
Published: (2024)

Comparative Analysis of Retrieval Systems in the Real World
by: Mozolevskyi, Dmytro, et al.
Published: (2024)

Towards Outcome-Oriented, Task-Agnostic Evaluation of AI Agents
by: AlShikh, Waseem, et al.
Published: (2025)

OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web
by: Kapoor, Raghav, et al.
Published: (2024)

Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention
by: Vasudev, Rakshith, et al.
Published: (2026)

RetryGuard: Preventing Self-Inflicted Retry Storms in Cloud Microservices Applications
by: Tavori, Jhonatan, et al.
Published: (2025)

R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
by: Shi, Weijie, et al.
Published: (2026)

Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
by: Nishimori, Soichiro, et al.
Published: (2026)

Exploring mental models of SEN among teachers of English for academic purposes: Themes and entanglements
by: Susie Russak, et al.
Published: (2026)

Finite Dimensional Lattice Codes with Self Error-Detection and Retry Decoding
by: Xue, Jiajie, et al.
Published: (2025)

Retrying vs Resampling in AI Control
by: Lucassen, James, et al.
Published: (2026)

Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection
by: Lee, Kyungjae, et al.
Published: (2024)

Analyzing the Impact of the Knowledge Management Process on the Banking Sector Performance: By Using the Partial Least Square Method
by: Khalil M. A. Al‐Muayad, et al.
Published: (2024)

Building High-Availability Microservices with Circuit Breakers and Retries
by: Raju Dachepally
Published: (2025)

Finite-Time Regret Analysis of Retry-Aware Bandits
by: Tong, Bingkui, et al.
Published: (2026)

MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction
by: Huang, Yue, et al.
Published: (2025)

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
by: Li, Jiaqi, et al.
Published: (2025)

When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity
by: Naseer, Kiran, et al.
Published: (2026)

Robust User Identification in Massive MIMO Systems Using Compressed Sensing Techniques
by: Ubaid Umar, et al.
Published: (2025)

Understanding AI Evaluation Patterns: How Different GPT Models Assess Vision-Language Descriptions
by: Abdoli, Sajjad, et al.
Published: (2025)

Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
by: Chen, Kunfeng, et al.
Published: (2026)

Why Retrying Fails: Context Contamination in LLM Agent Pipelines
by: Yang, Zhanfu
Published: (2026)

Reinforced Self‐Affirmation Method: Metamemory Monitoring and Control Mechanisms
by: Laura Melisa Buitrago Roa, et al.
Published: (2026)

Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation
by: Min, Do June, et al.
Published: (2024)

Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
by: Lara, Luis, et al.
Published: (2026)

SemanticFeels: Semantic Labeling during In-Hand Manipulation
by: Khalil, Anas Al Shikh, et al.
Published: (2026)

Specification of Sensing Coverage Zones in Two‐Dimensional Acoustic Target Localization
by: Muayad Ghazy Saham Al-kharsa, et al.
Published: (2025)

On the Loss and Propagation of Modulus of Continuity for the Two-Dimensional Incompressible Euler Equations
by: Khalil, Karim R. Shikh
Published: (2024)

Self-Evolved Reward Learning for LLMs
by: Huang, Chenghua, et al.
Published: (2024)

Reward Is Enough: LLMs Are In-Context Reinforcement Learners
by: Song, Kefan, et al.
Published: (2025)

Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models
by: Zhou, Xin, et al.
Published: (2025)

Rewarding Reflection
by: Harvey, Carl A., II
Published: (2008)

Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey
by: Lamba, Preeti, et al.
Published: (2025)

D10Z-MIZAN Phase-0 Stack v1.1: OracleReceipt_ΦW v1.1 + ArbitrationReceipt v1.0 — Production-Grade Sovereign Attestation
by: Al Thani, Jamil
Published: (2026)

Grounded Robotics: Cryptoeconomic Assurance Infrastructure as Mandatory Certification Layer for Humanoid Systems
by: Al Thani, Jamil
Published: (2026)

Resolution of the Leopoldt Conjecture via Coherent Nodal Phases in the D10Z Framework
by: Al Thani, Jamil
Published: (2025)

The D10Z Resolution of the Beal Conjecture: Spectral Coherence as Prime Factor Correlation in the Spiderweb Fabric
by: Al Thani, Jamil
Published: (2025)

ArbitrationReceipt v1.0: Supranodal Resolution Layer for Inter-Node Conflict Management — MIZAN Governance Framework
by: Al Thani, Jamil
Published: (2026)

F = f·v(Zₙ): The Equation That Replaces E = mc²
by: Al Thani, Jamil
Published: (2025)