arXiv:2608. 19653v1 Announce Type: cross Abstract: Autonomous agents for machine learning experimentation must navigate heterogeneous repositories, repair training pipelines, and evaluate candidate improvements under realistic compute constraints.
arXiv:2607. 29626v1 Announce Type: new Abstract: As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important.
arXiv:2602. 02905v2 Announce Type: replace Abstract: Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge.
arXiv:2607. 20468v1 Announce Type: new Abstract: AI agents are increasingly used to automate research and development tasks, yet existing benchmarks typically evaluate them on prescribed workflows or narrow action spaces.
arXiv:2606. 04261v1 Announce Type: new Abstract: Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback.
arXiv:2603. 17216v2 Announce Type: replace Abstract: With the advent of AI agents, automated scientific discovery is becoming an increasingly plausible goal.
The paper introduces Humanize MLE Agents (HMA), a workflow that alternates two agents across sessions on a shared workspace, limiting each session to at most k experiments and resetting context between sessions. This approach, modeled as a context‑reset semi‑Markov decision process, outperforms single‑agent baselines, achieving a 78.2% any‑medal rate on 75 Kaggle MLE‑bench tasks—8.0 points higher than the best open‑source baseline and using only a quarter of its time budget. Across six heterogeneous agent pairs, HMA improves the any‑medal rate by an average of 6.4 points, and a supplementary kernel‑optimization case reaches 878 cycles, within 1.6% of the community leaderboard leader.
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:2608. 12593v1 Announce Type: new Abstract: Discovery---formulating novel generalizations---is a central part of the scientific process.
arXiv:2607. 04395v1 Announce Type: new Abstract: Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA.
MaxKernel is a multi‑agent system designed to generate high‑performance custom kernels for TPUs. It offers three paradigms: a Human‑in‑the‑Loop agent for collaborative design, an Autonomous agent that runs a fully automated optimization loop, and a Graph‑Based Autonomous Search for global exploration. All paradigms share specialized sub‑agents for planning, implementation, debugging, testing, and profiling, and the system consistently matches expert hand‑tuned baselines on the JaxBench suite and real‑world workloads.
arXiv:2604. 17931v3 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents.
arXiv:2608. 16798v1 Announce Type: cross Abstract: Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment.