arXiv:2607. 06906v1 Announce Type: new Abstract: Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value.
By Muayad Sayed Ali, Aliaksandra Novik, Anji Boddupally, Artem Yavorskyi, Chris Nickerson, Daniel Rica, Emily DuGranrut, Felix Leung, Garrett Prince, Grace Barnett, Heath Robinson, Hosain Al Ahmad, Jesse Resnick, Juan Carlos Farah, Jyothi Swaroop Meruga, Leonid Kuznetsov, Luke Gorham, Marie Schmoll, Michael Paciullo, Saumya Das, Sharath Sheripally, Tommy Griscom, Mykyta Osadchyi, Neha Mantri, Nick Westrum, Olivia Benowitz, Parikshith Kulkarni, Radik Chernyshov, Rakshith Vasudev, Rohith Nadimpally, Vikas Gangadevi, Waseem AlShikh
Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value. Falling per-token prices mask the pattern; total spend rises anyway.
JevAgentHarness is a new framework that benchmarks, deploys, and trains decision models to share control with large language models (LLMs) in agentic tasks. It introduces AgentDecisionBench to evaluate decision models from isolated questions to full agent control, revealing that accurate isolated decisions still miss many tasks and that naïve delegation can reduce success. By fitting confidence thresholds per choice and training a 4B decision model on states after agent mistakes, JevAgentHarness achieves high task success while cutting cost and speeding up execution, with results and resources made publicly available.
By Kunlun Zhu, Tao Feng, Xu Han, Heng Wang, Ling Yang, Xiangru Tang, Jiaxuan You, Heng Ji
arXiv:2610.15093v1 Announce Type: cross
Abstract: AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this...
By Pramod Kumar, Raj Kumar Pandey
The paper reports on Grayhat Developers’ experience deploying a hybrid AI stack that combines local open‑source models with commercial agents. After finding local models too slow for complex coding tasks, the team kept commercial agents for those tasks while using local models for lower‑complexity work, documentation sync, and tool coordination, reducing commercial AI usage by 27–36%. The initial self‑hosted deployment suffered from UX friction, but a centrally configured deployment improved adoption.
By Saad Ahmed Bazaz, Talha Amjad, Abdurrehman Subhani, Sohaib Ahmed Bazaz, Abdullah Aamir
Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large LLM at every step, which makes long tasks slow...
arXiv:2608. 04804v1 Announce Type: cross Abstract: Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone.
By Ishaan Bhola, Adithyan Krishnan, Mukunda NS
The paper discusses how large enterprises can adopt the harness paradigm to overcome limitations of traditional coding approaches. It reviews recent findings that harnesses outperform complex architectures at the task level, that harness choice drives benchmark variance more than model choice, and that governance is the main barrier to enterprise adoption. The authors propose a unified harness architecture that keeps code identical across deployments, simplifying review and audit processes.
By George Juraj Salapa
arXiv:2606. 18543v1 Announce Type: new Abstract: Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service.
By Haozhe Chen, Karthik Narasimhan, Zhuang Liu
StoreBench is a live‑commerce environment where an autonomous agent runs a mid‑size online apparel store on a production‑grade backend, facing continuous customer orders, supplier price changes, and market shocks. The agent uses the same 29 merchant tools as a human operator, with a windowed operation budget that ties simulated time to actions, ensuring that model latency does not affect the simulation. Seven large language models were evaluated across 11 scenarios of 30–45 days and a full simulated year, but none matched the scripted smart‑triage policy, and human experts outperformed all models.
By Daksh Raghuvanshi, Ved Vedere, Yifan Wang
The paper introduces HARNESSEVO, a method that decomposes a large language model’s harness into four independently evolvable components—role, task‑strategy, tool/format‑rules, and reflection/control. Experiments on ALFWorld show that overall success rates are similar to flat‑string evolution, but the reflection/control component alone accounts for most of the performance gains. The study also finds that evenly distributing optimization budget across all slots can be detrimental; concentrating resources on the high‑credit control slot recovers lost performance, while on WebShop all slots remain ineffective, suggesting task‑specific differences in harness value.
By Michael Nguyen, Wei Chen Tan, Nurul Aisyah Hassan, Arvind Raman, Li Hua Lim, Ahmad Faiz Razak
The paper introduces $ au^ au$-Bench, a benchmark that turns the construction of AI agents into a measurable task. In this environment a developer agent receives real business records, client requirements, a production API, an existing codebase, and constraints on cost and models, and must deliver a complete customer‑service agent. The benchmark evaluates performance by deploying the agent against simulated users, revealing that current state‑of‑the‑art models achieve only 23.9% success while an expert‑written reference scores 82.2%.
By Quan Shi, Keshav Dhandhania, Karthik Narasimhan, Victor Barres