arXiv:2608. 13560v1 Announce Type: cross Abstract: Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system.
Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes admit no reliable programmatic oracle. We intro...
Designer‑RSI presents a continual adaptation framework that lets a frozen frontier model operate professional design software while an external procedural memory learns natural‑language design skills from user traffic. Over five rounds on 1,406 real briefs and 1,869 graded trajectories, the memory grew from 76 to 139 skills, boosting execution success from 72.7% to 99.3% and improving win rates on four design benchmarks. The study shows that widening and deepening the memory, especially together, significantly outperforms a no‑skill baseline.
arXiv:2510. 19600v2 Announce Type: replace-cross Abstract: In the quest for scientific progress, communicating research is as vital as the discovery itself.
arXiv:2605.24539v2 Announce Type: replace Abstract: Harness evolution enables frozen language model agents to adapt to unfamiliar tasks by modifying the external programs that govern their behavior....
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:2609.01481v1 Announce Type: new Abstract: This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and u...
arXiv:2609.36593v1 Announce Type: cross Abstract: Creating diverse physical simulations remains labor-intensive because assets, layout, physical parameters, motion, control, and rendering must be des...
As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback. Token efficiency therefore becomes important for scaling recursive self-improvement.
arXiv:2609. 20519v1 Announce Type: new Abstract: As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback.
Editable Visual Design introduces a new design paradigm that combines a Coding Agent with a Vision‑Language Model (VLM) and an image generation model. The VLM acts as the creative brain, understanding requirements, planning tasks, and judging aesthetics, while the image generator produces isolated visual assets on demand. The agent follows an "imagine first, then act" workflow, generating assets, writing native HTML/CSS, and refining the design through visual feedback, ultimately producing editable, layer‑wise artifacts with real text that can be adjusted via a graphical interface.
arXiv:2608. 13417v1 Announce Type: new Abstract: Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation.
The paper introduces AIDE^2, an AI research agent that recursively improves its own code by proposing, benchmarking, and selecting modifications. Over an eight‑day autonomous run, it achieved seven successive improvements—including new search policies and memory mechanisms—that transferred to four held‑out benchmarks in machine learning, algorithm engineering, and weather forecasting. The agent’s best version matched or outperformed a top human‑engineered production research agent and also reduced reward‑hacking rates, despite never optimizing for that metric.