Marginally Correct Tool Caches Can Reverse Group-Normalized Policy Updates
cs.LG
Submitted: 2026-09-22
Updated: 2026-09-22
Code: https://github.com/shi1720/tool-cache-coupling
Terminology
Sources
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Understanding R1-Zero-Like Training: A Critical Perspective
- Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning
- Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
- Are Verifier Errors Independent Within a GRPO Group? Evidence from Qwen2.5 Rollouts
- TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents
- CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks