arXiv Machine Learning July 30, 2026 By Yicheng Feng, Yan Zhang, Yan Cheng, Wei Qi

Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents

Read the original on arXiv Machine Learning →

arXiv:2607. 27083v1 Announce Type: new Abstract: As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental tool-selection challenge: acquiring too few tools leaves the task under-informed, while too many adds cost, context load, and privacy exposure.

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

arXiv AI

Jun 9

How Many Tools Should an LLM Agent See? A Chance-Corrected Answer

arXiv:2605. 24660v2 Announce Type: replace-cross Abstract: Before an LLM agent can use a tool, a retrieval system must decide which candidate tools to show to the agent.

By Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh, Joey Blackwell II

llms agents reinforcement-learning benchmarks

arXiv AI

Aug 11

From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Based LLM Agents

arXiv:2608. 09168v1 Announce Type: new Abstract: Agent skills are increasingly used to equip large language model (LLM) agents with reusable procedural knowledge.

By Liang He, Jingbo Wen, Hongyu Gu, Hao Li, Haoyu Wang, Yixiong Chen, Kangning Cui, Xilu Wang

llms agents

arXiv AI

Jun 8

To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling

arXiv:2605. 00737v2 Announce Type: replace Abstract: Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities.

By Qinyuan Wu, Soumi Das, Mahsa Amani, Arijit Nag, Seungeon Lee, Krishna P. Gummadi, Abhilasha Ravichander, Muhammad Bilal Zafar

llms agents

arXiv Machine Learning

Jun 11

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

arXiv:2606. 12344v1 Announce Type: new Abstract: General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring.

By Mengyu Zheng, Kai Han, Boxun Li, Haiyang Xu, Yuchuan Tian, Wei He, Hang Zhou, Jianyuan Guo, Hailin Hu, Lin Ma, Chao Xu, Guohao Dai, Lixue Xia, Yunchao Wei, Yunhe Wang, Yu Wang

agents benchmarks

arXiv AI

Aug 7

EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents

arXiv:2608. 05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic.

By Jie Wu, Ming Gong, Feixiang Cheng, Qinqin Zhao

llms agents benchmarks

arXiv AI

Aug 6

Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First

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

llms agents benchmarks

Related stories

How Many Tools Should an LLM Agent See? A Chance-Corrected Answer

From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Based LLM Agents

To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents

Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First