Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-02
Sources
- Program Synthesis with Large Language Models
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
- Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game
- Ensembles of Low-Rank Expert Adapters
- The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters
- LoRA ensembles for large language model fine-tuning
- Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
- LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs
- On Memorization of Large Language Models in Logical Reasoning
- Qwen2.5 Technical Report
- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
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