Entity · paper

Reinforcement Learning for Code Optimization

paperactiveprovisionalreinforcement-learning-for-code-optimization-96fea7a5·1 events·first seen 46h ago

Aliases: Reinforcement Learning for Code Optimization

Co-occurring entities

More like this (12)

Reinforcement Learning for Code Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design Physics-EnhAnced Reinforcement Learning Gradient-Guided Reward Optimization Reinforcement Learning with Metacognitive Feedback SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0 TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization reinforcement learning from verifier feedback Entropy-Regularized Reinforcement Learning rule-based reinforcement learning rewards Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code

Recent events (1)

6arXiv · cs.AI·46h ago·source ↗

Reinforcement learning for code optimization via calibrated timing rewards and adapted GRPO

A new arXiv preprint addresses the challenge of extending RL-based code generation to code optimization, where execution time is added to the reward signal. The authors identify three failure modes (measurement noise, reward sparsity, GRPO instability) and propose a three-stage solution: a new benchmark (DMC-Optim) with calibrated timing, a composed correctness-plus-speed reward with offline simulator, and adapted GRPO training. On Qwen 2.5 7B and CWM 32B, strict top-50% pass@1 improves from 18.0% to 31.3% and 30.7% to 50.4% respectively, with larger gains at stricter percentiles, while preserving correctness scores.

Evaluation and Benchmarking Agent and Tool Ecosystem LCB GRPO DMC-Optim +3 more