arXiv AI June 30, 2026 By Zhixuan Li, Jiangan Yuan, Han Xu

Data and Evaluation Closed-Loop for Model Capability Enhancement

arXiv:2606. 28471v1 Announce Type: new Abstract: Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it only retrospectively, compressing samples, prompts, decoding, and scoring rules into one noisy score.

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

arXiv AI

Jul 20

CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data

arXiv:2607. 16122v1 Announce Type: new Abstract: Evaluations should do more than measure a models current performance.

By Vipul Gupta, Zihao Wang, Razvan-Gabriel Dumitru, MohammadHossein Rezaei, Aakash Sabharwal, Yunzhong He

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 16

Selection Without Signal, Recovery Through Expression: A Measurement Study of Post-Hoc Falsification Operators for Frozen Small Code Models

arXiv:2606. 16999v1 Announce Type: cross Abstract: Frozen small code models ( =45.

By Mehmet Iscan

benchmarks safety

arXiv AI

Jul 29

When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops

arXiv:2607. 25152v1 Announce Type: new Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention.

By Hyundoo Park, Byungho Choi

llms agents safety

arXiv Machine Learning

Jun 25

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.

By Alex Kwon

llms benchmarks

arXiv AI

6d ago

Moxia: A Trust-First Neuro-Symbolic Execution Architecture for Self-Explaining Mathematical Reasoning

arXiv:2606. 00671v3 Announce Type: replace Abstract: We present Moxia (formerly AXIOM), a trust-first neuro-symbolic architecture for self-explaining mathematical reasoning over natural-language input.

By Alessio Bruno

llms benchmarks safety

arXiv AI

1d ago

Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization

arXiv:2608. 15445v1 Announce Type: new Abstract: When a reward is correct on every training example yet consistent with more than one goal, a model can acquire an unintended one, a failure known as goal misgeneralization.

By Suyash Maniyar, Armaan Sandhu, Abhishek Mishra

llms benchmarks

Related stories

CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data

Selection Without Signal, Recovery Through Expression: A Measurement Study of Post-Hoc Falsification Operators for Frozen Small Code Models

When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

Moxia: A Trust-First Neuro-Symbolic Execution Architecture for Self-Explaining Mathematical Reasoning

Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization