arXiv AI
GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 15
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
arXiv:2609.14857v1 Announce Type: new Abstract: Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve executio...
arXiv Computation and Language
Aug 21
Self-Harness: Harnesses That Improve Themselves
arXiv:2606. 09498v3 Announce Type: replace Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment.
arXiv AI
2d ago
Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.
arXiv AI
Sep 25
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
The paper introduces Growing Harness, a training method that transforms recurring control logic in large language model agents into reusable executable code, reducing reliance on the model for task-specific decisions. By using strategy-free scaffolds, failure-guided code repair, and success-first gating, the approach learns a shared harness that improves performance across multiple benchmarks and model sizes. Experiments on BrowseComp-Plus and WebArena-Verified show significant gains in success rates and substantial reductions in LLM calls and inference cost compared to traditional tool‑calling agents.
arXiv AI
Jul 29
Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification
arXiv:2607. 25904v1 Announce Type: new Abstract: Graphical user interface task evaluation aims to determine whether a GUI agent has successfully completed a user instruction.
arXiv AI
Aug 18
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
arXiv:2608. 15930v1 Announce Type: new Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution.