arXiv AI October 16, 2026 By Swati Gupta, Tianjiao Li

When is a better LLM worth paying for? Stochastic Optimization with Switching Mixed-Fidelity Oracles

The paper investigates when it is worthwhile to pay for higher‑fidelity large language models (LLMs) in stochastic optimization tasks. It introduces two cost‑aware algorithmic frameworks that adaptively switch between mixed‑fidelity first‑order oracles, one for known bias and one for unknown bias, and demonstrates that these methods can reduce cumulative cost while maintaining accuracy. Experiments with synthetic data and LLM completions confirm that the adaptive policies skip expensive oracles and achieve comparable performance to fixed high‑fidelity approaches.

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 AI.

arXiv Machine Learning

Oct 5

Online Verification of Language Model Responses Under Cost Constraints

The paper introduces OMVV, an online multi-verifier algorithm that maintains a pool of weak verifiers with varying costs and performance. It adaptively selects a verifier each round using an online score combiner and exponential-weights routing, providing distribution-free guarantees on false-accept and false-reject rates. Experiments on reasoning benchmarks show OMVV achieves higher accuracy at lower verification cost than any single fixed verifier across different budgets.

By Erfan Hajihashemi, Yanning Shen

llms benchmarks

arXiv AI

Jun 15

Rethinking the Trust Region in LLM Reinforcement Learning

arXiv:2602. 04879v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm.

By Penghui Qi, Xiangxin Zhou, Zichen Liu, Tianyu Pang, Chao Du, Min Lin, Wee Sun Lee

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Jun 9

Agentic Search for Counterfactual Recourse under Fixed LLM Budgets

arXiv:2606. 08696v1 Announce Type: cross Abstract: Counterfactual recourse aims to provide actionable feature changes that would alter an unfavorable decision made by a predictive model.

By Yasuo Tabei

llms agents efficiency

arXiv Machine Learning

Jul 10

Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models

arXiv:2607. 08665v1 Announce Type: new Abstract: Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle.

By Teng-Ruei Chen

llms benchmarks

arXiv Machine Learning

Jun 16

Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning

arXiv:2606. 14970v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data.

By Dmitriy Bystrov, Daniil Medyakov, Dmitry Bylinkin, Aleksandr Beznosikov

llms fine-tuning

arXiv Machine Learning

Jun 11

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning

arXiv:2601. 04710v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation.

By Feihu Jin, Shipeng Cen, Ying Tan

llms fine-tuning benchmarks

One email a morning, machine-written

Related stories

Online Verification of Language Model Responses Under Cost Constraints

Rethinking the Trust Region in LLM Reinforcement Learning

Agentic Search for Counterfactual Recourse under Fixed LLM Budgets

Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models

Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning