The article "Coding Agents Can Solve the Task — But How Much Work Did They Waste?" examines the performance of coding agents using real repositories and seeded agent decisions. It reports on 50,400 runs, highlighting metrics such as wasted turns, patch churn, and the effectiveness of different harness rules. The study provides insights into how these agents manage code modifications and the efficiency of their decision-making processes.
The article titled "Where Does the Money Go Across Long-Running Coding Agents?" explores the financial aspects of maintaining and operating coding agents over extended periods. It highlights the costs associated with controlling these agents and examines how resources are allocated during their lifecycle.
The article "How to Effectively Solve 100+ Tasks with Claude Code" discusses strategies for working more efficiently with coding agents. It focuses on practical approaches to manage and complete a large number of tasks using Claude Code. The post was originally published on Towards Data Science.
Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to software projects, introducing new forms of human-agent collaboration in software development. While prior studies have examined PR-level outcomes of agent-generated contributions, less is known about how agentic coding tools are adopted and managed at the project level.
arXiv:2608.29204v2 Announce Type: replace-cross Abstract: Coding agents now complete development tasks in real software projects and submit the results as pull requests. A pull request shows the outc...
arXiv:2607. 14037v1 Announce Type: cross Abstract: Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to software projects, introducing new forms of human-agent collaboration in software development.
The hidden cost of asynchronous systems, how tiny CPU tasks quietly became our biggest bottleneck while scaling hundreds of LLM agents. The post Why Adding More AI Agents Made Our System Slower appeared first on Towards Data Science .
Multi-agent coding systems don't necessarily fail because agents can't communicate. They can fail because important commitments made in conversation have nowhere to live afterward. The post Multi-Agen...
arXiv:2607. 01418v1 Announce Type: cross Abstract: Organizations rolling out agentic command line tools like Anthropic's Claude Code and GitHub's Copilot CLI need to know who will try them, who will keep using them, and whether the tools produce enough output to justify their cost.
The paper investigates cost-inefficient behaviors in coding agents, analyzing 1,200 trajectories from Claude Code and Mini-SWE-Agent on SWE-bench Verified. It identifies three main inefficiencies—subsumed retrieval, similar script generation, and test re-execution—that affect 79–98% of tasks and contribute up to 22.75% of costs. The study evaluates mitigation strategies, finding that developer-designed skills reduce costs by up to 41.73%, outperforming other approaches.
Simon Willison reflects on his experience with coding agents, noting that while they enable impressive feats, they also complicate software engineering. He emphasizes that fully harnessing their capabilities demands exceptional discipline and deep knowledge. The article highlights the dual nature of coding agents as both powerful tools and challenging additions to development workflows.
Optimise how you interact with your coding agents The post How to Organize All of Your Coding Agent Tasks appeared first on Towards Data Science .
AgentSWE is a new benchmark for agent software engineering that evaluates coding agents across three lifecycle stages: creating an agent from a natural‑language requirement, editing existing agent codebases, and optimizing toward a measurable target. The benchmark consists of 25 commission‑style tasks, where builders iterate on a few illustrative cases and are then tested on held‑out cases that cover the full requirement, with hard pass/fail gates or objective‑based grading. Experiments show that current coding agents fail to meet the requirements, revealing common failure modes such as overfitting, incomplete runtimes, and unsupported completion claims.