arXiv Machine Learning By Abhinav Anand, Sanjana Reddy Pachika, Shweta Verma, Mira Mezini

Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs

Read the original on arXiv Machine Learning →

The paper investigates whether reinforcement‑learning post‑training of code‑generating large language models can be done entirely offline using existing datasets, avoiding costly online code generation and GPU‑CPU communication. Experiments show that a few hours of offline RL can substantially boost zero‑shot code generation performance across models from 0.5 B to 7 B parameters, though the magnitude of improvement differs by model family.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI
3d ago

CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback

CHAI for LLMs is a framework that improves large language models’ performance on code‑mixed translation tasks by using LLMs as annotators to create preference data, applying reinforcement learning from AI feedback, incorporating LLM‑generated domain knowledge for iterative refinement, and evaluating on real‑world datasets. The approach yields a 68.45% average win rate over state‑of‑the‑art open‑source models in human‑adjudicated tests. It demonstrates a scalable method to enhance code‑mixed language understanding in open‑source LLMs.

By Wenbo Zhang, Aditya Majumdar, Asif Ekbal, Amulya Yadav
arXiv Machine Learning
Jun 11

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

arXiv:2606. 12370v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines.

By Yucheng Li, Huiqiang Jiang, Yang Xu, Jianxin Yang, Yi Zhang, Yizhong Cao, Yuhao Shen, Fan Zhou, Rui Men, Jianwei Zhang, An Yang, Bowen Yu, Bo Zheng, Fei Huang, Junyang Lin, Dayiheng Liu, Jingren Zhou
arXiv Machine Learning
Sep 1

Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environment

Agnostics is a language‑agnostic post‑training pipeline that uses reinforcement learning with verifiable rewards (RLVR) to improve large language models on low‑resource programming languages. By rewriting unit‑test datasets into a language‑independent I/O format, providing a short configuration for compiling and running code, and employing a single verifier that judges code by observable behavior, Agnostics eliminates the need for language‑specific engineering. Applied to Lua, Julia, R, OCaml, and Fortran, it boosts Qwen‑3 4B to rival larger models, scales to diverse families, and achieves new state‑of‑the‑art pass@1 on MultiPL‑E and a new multi‑language LiveCodeBench.

By Aleksander Boruch-Gruszecki, Yangtian Zi, Zixuan Wu, Tejas Oberoi, Carolyn Jane Anderson, Joydeep Biswas, Arjun Guha
arXiv Machine Learning
Jul 10

Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation

arXiv:2607. 07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia.

By Didula Samaraweera, Anjana Supun, Srinath Perera
Hugging Face Trending Papers
Jun 10

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance.

arXiv Machine Learning
Aug 24

When to Ponder: Adaptive Compute Allocation for Code Generation via Test-Time Training

The paper introduces PonderTTT, a gating strategy that uses the self‑supervised reconstruction loss from a Test‑Time Training (TTT) layer to decide when to apply TTT updates during inference. The gating mechanism is training‑free, relying only on a single scalar threshold that is calibrated on unlabeled data and updated via exponential moving average to keep the desired update rate. Experiments on GPT‑2 models (124M–1.5B) for code language modeling show that this approach achieves 82–89% oracle recovery and outperforms random skip baselines, reducing loss on out‑of‑distribution languages by up to 16%.

By Gihyeon Sim