arXiv Machine Learning August 11, 2026 By Srinivasan Manoharan, Junhua Zhao, Fangbo Tu, Haifeng Wu, Jian Wan, Maliah Rajan M, Ashwin Hegde, Mithun Sasidharan, Kalyan Chakravarthi Podamekala

Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing

Read the original on arXiv Machine Learning →

arXiv:2608. 08528v1 Announce Type: new Abstract: Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries, escalations, and developer wait time are included.

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

arXiv AI

Jun 4

Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation

arXiv:2606. 04402v1 Announce Type: new Abstract: Modern reasoning models can allocate different amounts of test-time computation, such as thinking tokens, model calls, or compute budget, to different tasks.

By Jingbo Wen, Liang He, Ziqi He

benchmarks

arXiv AI

Jul 28

CRAFT: Learn the Schema, Execute the Plan

arXiv:2607. 22642v1 Announce Type: new Abstract: Enterprise coding agents translate natural-language analytical requests into executable code over proprietary APIs, schemas, and metric definitions.

By Aakash Kolekar, Sahika Genc, Shahriar Shariat, Bunyamin Sisman, Tibor Mezi, Barbara Poblete, Shree Vandana Kachroo, Calvin Chi, Parth Parmar, Ari Singer, Prayaas Jain, Cindy Barker, Benoit Dumoulin

llms agents reinforcement-learning fine-tuning

arXiv Machine Learning

Jul 30

REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage

arXiv:2604. 01527v4 Announce Type: replace-cross Abstract: Production deployment of AI coding agents requires fast, reproducible evaluation signals.

By Smriti Jha, Matteo Paltenghi, Chandra Maddila, Vijayaraghavan Murali, Shubham Ugare, Satish Chandra

llms agents benchmarks

arXiv AI

Jul 14

Agentic Routing: The Harness-Native Data Flywheel

arXiv:2607. 11399v1 Announce Type: cross Abstract: Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification.

By Xinchen Liu, Hang Zhou, Yingjie Zong, Yuchuan Tian, Liuyang Song, Shuo Zhang, Yulong Li, Wei He, Mengyu Zheng, Runke Liu, Siyang Cheng, Xiang Kuang, Hailin Hu, Kai Han, Yunhe Wang

llms agents benchmarks

arXiv AI

Jun 29

Agent-as-a-Router: Agentic Model Routing for Coding Tasks

arXiv:2606. 22902v3 Announce Type: replace Abstract: Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all.

By Pengfei Zhou, Zhiwei Tang, Yixing Ma, Jiasheng Tang, Yizeng Han, Zhenglin Wan, Fanqing Meng, Wei Wang, Bohan Zhuang, Wangbo Zhao, Yang You

llms agents benchmarks

arXiv AI

Aug 7

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

arXiv:2608. 06301v1 Announce Type: new Abstract: As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them.

By Varun Ursekar, Apaar Shanker, Yash Maurya, Shehab Yasser, Vijay S. Kalmath, Veronica Chatrath, Yuan Xue

llms agents benchmarks

Related stories

Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation

CRAFT: Learn the Schema, Execute the Plan

REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage

Agentic Routing: The Harness-Native Data Flywheel

Agent-as-a-Router: Agentic Model Routing for Coding Tasks

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization