arXiv Machine Learning July 31, 2026 By Iliya Mirzaei

Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

Read the original on arXiv Machine Learning →

arXiv:2607. 28576v1 Announce Type: cross Abstract: Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a single chain of thought.

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

arXiv Machine Learning

Jul 30

Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models

arXiv:2607. 26117v1 Announce Type: cross Abstract: Self-repair - returning a failed program to the model together with its test output and asking for a correction - is a standard component of code agents, and is almost always evaluated against a baseline that does not retry at all.

By Yuvraj Verma

agents

arXiv AI

Aug 7

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

arXiv:2608. 05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity.

By Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Lena Trigg, Ali Subhan, Muhammad Ali, Dean F. Hougen

llms reinforcement-learning

arXiv AI

Jun 30

When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling

arXiv:2606. 28661v1 Announce Type: cross Abstract: People overthink; language models over-sample, and the extra effort can talk both into a worse answer.

By Yong Yi Bay, Kathleen A. Yearick

llms benchmarks

arXiv AI

Aug 11

REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

arXiv:2608. 07931v1 Announce Type: new Abstract: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment.

By Zhengze Huang, Luyang Yu, Di Hong, Xinzhe Huang, Wanyu Lin, Zhixuan Chu, Zhan Qin, Tianhang Zheng

benchmarks safety

arXiv AI

Jul 14

Interaction Scaling: Grounding the Third Axis of Test-Time Compute

arXiv:2607. 11598v1 Announce Type: new Abstract: There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one.

By Bojie Li, Noah Shi

llms multimodal

arXiv AI

6d ago

The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance

arXiv:2608. 11694v1 Announce Type: cross Abstract: A benchmark score comes from a single phrasing of each problem.

By Shailja Thakur, Sungeun An, Chad DeLuca, Hima Patel

llms benchmarks

Related stories

Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling

REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

Interaction Scaling: Grounding the Third Axis of Test-Time Compute

The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance