You Only Edit Once: Incentivizing In-Context Capability of LLMs via Local Demonstration Refinement
cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- The Llama 3 Herd of Models
- RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
- Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
- Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
- Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
- Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
- TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
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