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.
arXiv:2607. 07984v1 Announce Type: new Abstract: Neural architecture search (NAS) methods have grown increasingly efficient, yet they remain bounded by manually engineered search spaces that require substantial domain expertise and must be rebuilt for every new task.
arXiv:2606. 30111v1 Announce Type: cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules.
arXiv:2606. 30111v2 Announce Type: replace-cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules.
arXiv:2607. 06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures.
Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectural design space, but current systems still rely on researcher intuition to choose where information is stored, how observations are processed, and how model calls are connected.
Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness.
arXiv:2606. 02461v1 Announce Type: new Abstract: Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes.
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:2606. 02461v2 Announce Type: replace Abstract: Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes.
arXiv:2608. 18066v1 Announce Type: new Abstract: Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature.
Two prompts can request the same code change and produce the same correct patch, yet cause a coding agent to perform radically different kinds and amounts of work. We study this effect in a preregistered benchmark spanning 4,644 valid runs, 24 deterministic coding tasks, seven reasoning models, and two real agent harnesses.
arXiv:2606. 12848v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for tasks once reserved for trained researchers, including hypothesis generation, specification choice, and drafting conclusions.