arXiv:2608. 13940v1 Announce Type: new Abstract: AI research agents (AIRA) can now propose, implement, and evaluate their own machine learning experiments, but progress on frontier tasks is throttled by cost: a candidate solution can be written in minutes, whereas evaluating it can take hours to days of GPU time.
arXiv:2610.07625v1 Announce Type: cross Abstract: Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay...
The paper investigates how reinforcement learning post‑training of large language models (LLMs) tends to sharpen existing behaviors, improving single‑shot accuracy but reducing solution coverage. It shows that pre‑trained LLMs, when paired with a lightweight inference harness, can outperform post‑trained models in coverage for agentic tasks that require multi‑turn tool use. The authors introduce the Sharpening Tax metric to quantify this trade‑off, analyze its prevalence across 14 model pairs and 42 benchmark cases, and propose a Bayesian sampler, PTGS, that mitigates the tax by adapting sampling temperature to prompt difficulty.
arXiv:2511. 00802v2 Announce Type: replace-cross Abstract: With data-driven development now widely adopted, online A/B testing is an established method for measuring the effects of new technologies.
arXiv:2609.07611v1 Announce Type: new Abstract: Scientific ideation is the capacity to formulate novel and testable hypotheses from scientific evidence, and autonomous AI scientists depend on it. Exi...
arXiv:2605. 08678v3 Announce Type: replace Abstract: Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes.
arXiv:2602. 11354v3 Announce Type: replace Abstract: The literature has witnessed an emerging interest in AI agents for automated assessment of scientific papers.
MLE-World is a world model fine‑tuned from Qwen3.5‑4B that predicts the terminal output of a machine learning program—such as error traces, training logs, and validation scores—directly from its code and data description, without executing the program. It also provides a confidence score indicating the likelihood that the prediction is correct. Using these predictions, the authors design five test‑time‑scaling policies that compare multiple candidate programs per step, executing only those with low confidence, and demonstrate that MLE‑World matches real outputs on 77.9% of held‑out programs and improves agent performance by up to 22.1% with fewer real executions.
The paper introduces CoPE, a method that trains language agents by adding multi‑step action targets to the policy backbone. By supervising each action forecasted from preceding histories, CoPE enables acting and forecasting to co‑evolve without extra inference cost. Across five benchmarks, CoPE outperforms existing RL baselines, achieving up to twice the sample efficiency on ScienceWorld and improving overall performance on realistic applications.
The paper presents a new scaling law for reward optimization in AI alignment, showing that performance scales as Θ(√min{log(M), K}), where M is the number of preference comparisons used to train a proxy reward model and K is the KL‑divergence budget relative to a reference policy. The authors derive this law using an information‑theoretic model, prove its tightness, and validate it with extensive experiments involving a 70B gold reward model and smaller proxy models (0.6B–4B). The empirical results demonstrate a strong fit (R² 97–99 %) across different model sizes, noise levels, and optimization methods, suggesting that reward optimization behaves like a simple selection task over IID Gaussian variables with noisy feedback.
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.
We study what happens when a single general-purpose large language model acts as the sole researcher on a long-horizon neural architecture design problem. The agent receives a scientific question, an initial hypothesis and motivation, a compute budget, and research affordances (source and experiment management, experiment tracking, literature access, and persistent memory), then autonomously proposes, implements, evaluates, and records experiments over an extended period.