The paper introduces Harness Primitives—reusable agent harness mechanisms mined from failed task trajectories—and a framework called STITCH that selects and composes these primitives into task‑specific harnesses at test time. This approach avoids generating or debugging harness code for each task, achieving up to 12‑point gains in task success over fixed harness baselines and outperforming human‑designed harnesses like Codex CLI. STITCH also demonstrates minimal test‑time overhead (2.7%) and scales efficiently with the size of the primitive library.
By Peng Kuang, Haibo Jin, Dehao Wu, Feiyang Deng, Xiaopeng Yuan, Jerry Wang, Haohan Wang
The paper investigates how environment-agnostic coding agents can be improved without environment-specific engineering. By modifying a Codex-based agent’s instruction to report difficulties and allow automatic continuation, the authors achieve higher mean scores on ARC‑AGI‑3 and AGI Maze, though performance on Terminal‑Bench remains mixed. A scripted controller that handles reset decisions partially recovers the advantage of a specialized agent, demonstrating that effective use of available information and procedures is crucial for these models.
By Sergey Rodionov
The paper introduces CTXAgent, a self‑controlled context management system for large language model agents that compacts conversation history when a token threshold is reached. It evaluates seven frontier models, comparing their ability to manage context with and without dedicated tools, and benchmarks performance across coding, scientific, and software engineering tasks. Results show that well‑managed models keep live context below 100k tokens, maintain high benchmark scores, and achieve significant cost reductions, with Claude Opus 5.5 outperforming its explicit configuration by 34% lower cost.
By Matthias Busch, Marius Tacke, Roland C. Aydin, Christian Feiler, Christian J. Cyron
arXiv:2606. 30573v1 Announce Type: new Abstract: We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks.
By Mohit Raghavendra, Anisha Gunjal, Aakash Sabharwal, Yunzhong He
The paper introduces RiseHarness, a framework that iteratively refines agent harnesses while keeping model weights fixed. It uses successful and failed runs under the same configuration to analyze failures, combining agent trajectories with runtime monitor traces to understand interactions between model actions and execution components. The framework then searches other harness frameworks for relevant implementations, adapts them, and validates changes through behavioral checks and repeated task evaluation, ultimately integrating mechanisms from multiple frameworks to improve reliability across tasks.
By Ruhan Wang, Yucheng Shi, Zongxia Li, Junyao Yang, Zhongzhi Li, Yue Yu, Haitao Mi, Dongruo Zhou, Leoweiliang
The paper introduces a framework for evaluating large‑language‑model agents by focusing on the interaction between the model and its execution harness. It defines five complementary metrics—Valid Completion Rate, Model‑Harness Fit, Cross‑Model Fit, Interaction Residuals, and Token Load—to assess how reliably agents finish tasks, how well harnesses support specific models, and the overall suitability across models. Using these metrics, the authors evaluate four general‑purpose harnesses and two native systems on six benchmarks, finding that harness rankings differ by model and task and that some harnesses consistently achieve high valid completion rates.
By Shao Zhang, Hangfan Zhang, Yuanyuan Shi, Hao Li, Min-Le Su, Kangcong Li, Jingping Wang, Chunjiang Mu, Chen Zhang, Yang Chen, Bo Zhang, Shuyue Hu