DecompRL is an RL method that learns modular code decomposition for LLMs, enabling exponential candidate generation via recombination to solve harder coding problems with lower GPU cost.
Language models can teach themselves to program better
7 Pith papers cite this work, alongside 17 external citations. Polarity classification is still indexing.
7
Pith papers citing it
17
external citations · external index
representative citing papers
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
A single LLM agent that injects and repairs its own bugs in real repositories improves SWE-bench Verified and Pro by +10.4 and +7.8 points, outperforming a human-data RL baseline.
FELA deploys specialized LLM agents in an evolutionary framework to generate, validate, and refine explainable features from heterogeneous industrial event logs, improving downstream model performance.
PseudoBridge uses LLM-synthesized pseudo-code to bridge NL semantics and PL logic plus logic-invariant style augmentation to boost robustness and generalization in code retrieval.
LLM-FE is a framework that treats feature engineering as LLM-driven program search with data feedback, reporting consistent gains over baselines on classification and regression tabular tasks.
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
citing papers explorer
-
DecompRL: Solving Harder Problems by Learning Modular Code Generation
DecompRL is an RL method that learns modular code decomposition for LLMs, enabling exponential candidate generation via recombination to solve harder coding problems with lower GPU cost.
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
Toward Training Superintelligent Software Agents through Self-Play SWE-RL
A single LLM agent that injects and repairs its own bugs in real repositories improves SWE-bench Verified and Pro by +10.4 and +7.8 points, outperforming a human-data RL baseline.
-
FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data
FELA deploys specialized LLM agents in an evolutionary framework to generate, validate, and refine explainable features from heterogeneous industrial event logs, improving downstream model performance.
-
PseudoBridge: Pseudo Code as the Bridge for Better Semantic and Logic Alignment in Code Retrieval
PseudoBridge uses LLM-synthesized pseudo-code to bridge NL semantics and PL logic plus logic-invariant style augmentation to boost robustness and generalization in code retrieval.
-
LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
LLM-FE is a framework that treats feature engineering as LLM-driven program search with data feedback, reporting consistent gains over baselines on classification and regression tabular tasks.
-
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.