CREDO: Variance-Guided Rubric Evolution for Replay-Corrected Credit Assignment
cs.AI
Submitted: 2026-09-21
Updated: 2026-09-21
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Group-in-Group Policy Optimization for LLM Agent Training
- DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
- Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
- Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
- Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
- When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training
- Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection