arXiv:2608. 13417v1 Announce Type: new Abstract: Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation.
arXiv:2609.08248v1 Announce Type: new Abstract: Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iterati...
arXiv:2606. 05080v1 Announce Type: new Abstract: Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts.
The paper introduces Strategy Accumulation and Guided Execution (SAGE), a two-stage framework that makes automated fine-tuning of large language models cumulative. In the first stage, a multi-agent pipeline uses Monte Carlo Tree Search to explore training strategies while a Distillation Agent records task-specific insights and cross-task confidence scores into a structured repository. In the second stage, SAGE retrieves relevant experience from this repository to guide training on new tasks, achieving a 12.4‑percentage‑point improvement over a baseline pipeline without accumulated experience on nine unseen tasks.
Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts. Yet existing benchmarks for frontier models primarily evaluate either single-turn responses or short-horizon agent trajectories, failing to capture the challenges of sustained iterative improvement over extended time horizons.
ASI‑Bench is a new benchmark that evaluates AI systems on their ability to conduct innovative exploration and autonomous scientific research across 11 domains, using 60 project‑level tasks. It progressively removes human methodological guidance to test whether AI can independently select methods, execute research, and produce verifiable results. Results from 18 state‑of‑the‑art agent–model configurations show a sharp performance drop when guidance is reduced, indicating current systems still rely heavily on human input.
arXiv:2606. 11926v1 Announce Type: cross Abstract: Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction.
Agentick is a unified benchmark for sequential decision‑making agents that evaluates RL, LLM, VLM, hybrid, and human agents on 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities via a single Gymnasium‑compatible interface. It includes a Coding API, oracle reference policies, pre‑built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation of 27 configurations and over 90,000 episodes shows no single approach dominates, with GPT‑5 mini leading overall, PPO excelling in planning and multi‑agent tasks, and the reasoning harness boosting LLM performance by 3‑10×, while ASCII observations outperform natural language.
arXiv:2607. 08964v1 Announce Type: new Abstract: AI agents have become capable of autonomously completing short, well-specified tasks.
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to...
The paper introduces ASPIRE, a benchmark that challenges language model agents to self‑evolve from vague, natural‑language goals without explicit evaluation metrics. In ASPIRE, agents must interpret the goal, select data and update strategies, and decide when to evaluate, all while the downstream tasks remain hidden. Experiments show that while agents can complete training loops, weight‑level improvements are sparse and unstable, and the best evolved harness still falls short of a strong engineered baseline.
arXiv:2606. 26859v1 Announce Type: new Abstract: Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results.
AREX-2 is a new approach that enhances the self‑improving ability of large language model agents by combining reflection—producing better solutions—and long‑horizon execution—maintaining effectiveness over many iterations. The method synthesizes improvement trajectories from machine‑learning and algorithmic programming tasks, providing verifiable feedback and sustained iteration. Trained on this data, an agent based on Qwen3.8‑27B achieves strong performance across multiple benchmarks and continues to improve as more iterative rounds are allowed.