When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL
cs.LG, cs.AI, cs.IR
Submitted: 2026-05-27
Updated: 2026-10-10
Terminology
Sources
- Concrete Problems in AI Safety
- Evaluating Large Language Models Trained on Code
- AutoNeural: Co-Designing Vision-Language Models for NPU Inference
- Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
- Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis
- Code Llama: Open Foundation Models for Code
- Proximal Policy Optimization Algorithms
- Gymnasium: A Standard Interface for Reinforcement Learning Environments
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Language to Rewards for Robotic Skill Synthesis
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks