arXiv AI August 5, 2026 By Janis Zenkner, Tobias Sesterhenn, Tim Grams, Christian Bartelt

Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer

arXiv:2608. 03461v1 Announce Type: new Abstract: Decomposition-based Programming-by-example (PBE) scales performance by splitting tasks into subtasks that a learned synthesizer solves: a decomposer predicts intermediate subgoals, and a synthesizer generates programs conditioned on them.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

safety

arXiv AI

Jun 18

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier

arXiv:2606. 18284v1 Announce Type: cross Abstract: The limiting resource for training agents via reinforcement learning (RL) is increasingly frontier task supply: valid, solvable tasks just difficult enough to train the current model.

By Lorenz Wolf, Connor Watts, Roger Creus Castanyer, Geoffrey Bradway, Maxwill Lin, Augustine N. Mavor-Parker, Matthew Daborn-Sargent

agents reinforcement-learning

arXiv Machine Learning

Jun 29

Learning to Reason with Curriculum II: Compositional Generalization

arXiv:2606. 27721v1 Announce Type: new Abstract: Compositional generalization, the ability to solve complex problems by combining solutions to simpler sub-problems, is a fundamental capability of both natural and artificial intelligence, and a key mechanism underlying chain-of-thought reasoning.

By Nived Rajaraman, Audrey Huang, Miroslav Dudik, Robert Schapire, Dylan Foster, Akshay Krishnamurthy

reinforcement-learning fine-tuning

arXiv Machine Learning

Aug 7

CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

arXiv:2608. 06352v1 Announce Type: new Abstract: Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning.

By Fanzhe Meng, Guoxin Chen, Jiale Zhao, Shuang Sun, Zhiyu Lin, Wayne Xin Zhao, Ruihua Song, Ji-Rong Wen, Kai Jia

agents safety

arXiv AI

Jun 2

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

arXiv:2606. 01286v1 Announce Type: cross Abstract: The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or provide useful training signal.

By Yangzhen Wu, Aaron J. Li, Wenjie Ma, Li Cao, Ziheng Zhou, Mert Cemri, Shu Liu, Yuran Xiu, Chenxiao Yan, Haikun Zhao, Bin Yu, Ion Stoica, Dawn Song

llms reinforcement-learning benchmarks

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

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 9

Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation

arXiv:2606. 09278v1 Announce Type: cross Abstract: Large Language Models frequently hallucinate in precision-critical domains such as technical diagramming and mechanical design, where outputs must satisfy strict geometric constraints.

By Rafael Cabral, Pang Zixi, Ziyi Shou, Shen Xin

llms benchmarks

Related stories

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier

Learning to Reason with Curriculum II: Compositional Generalization

CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

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

Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation