arXiv AI
Jul 28
Efficiency Matters in Autonomous Research
arXiv:2607. 24647v1 Announce Type: new Abstract: AI-driven autonomous research (AR) systems are becoming increasingly effective across a broad range of tasks.
Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems
arXiv:2606. 02863v1 Announce Type: new Abstract: AI-Driven Research Systems (ADRS) -- systems coupling LLMs with automated evaluation to discover algorithms, proofs, and designs -- are being optimized and adopted across domains, but the tools to analyze them have not kept pace.
Related stories
arXiv AI
Jul 21
Automated Discovery Has No Universally Superior Harness
arXiv:2607. 18235v1 Announce Type: cross Abstract: Autonomous discovery systems such as OpenEvolve and TTT-Discover are often used as general-purpose harnesses.
arXiv Machine Learning
Jun 30
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?
arXiv AI
Aug 10
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
arXiv:2608. 06714v1 Announce Type: new Abstract: Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods.
arXiv AI
Aug 11
Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets
arXiv:2608. 08189v1 Announce Type: new Abstract: LLM-driven program discovery relies on rapid evaluator feedback, but many scientific and engineering tasks require high-fidelity simulations, hardware execution, or physical experiments, making each evaluation expensive.
arXiv AI
Aug 10
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
arXiv:2608. 06871v1 Announce Type: new Abstract: Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear, feedback-driven interactions that produce emergent behavior, with applications from population dynamics and biology to economic policy and strategic decision-making.
arXiv AI
Aug 5
OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
arXiv:2602. 13769v3 Announce Type: replace Abstract: Automating heuristic design in complex, experiment-driven domains requires more than iterative mutation of solution algorithms.
Hugging Face Trending Papers
Aug 7
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods. We ask a fundamentally different question: how much of this search policy can be internalized by a single tool-using agent?
arXiv AI
Jun 26
Scientific discovery as meta-optimization: a combinatorial optimization case study
arXiv:2606. 26728v1 Announce Type: new Abstract: Scientific discovery is fundamentally an optimization problem, defined by a vast "state space" of theories and experiments, and an evaluation criterion based on quality, novelty, and validity.
arXiv AI
Jun 11
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
arXiv:2606. 11926v1 Announce Type: cross Abstract: Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction.
arXiv AI
Aug 6
Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection
arXiv:2608. 05085v1 Announce Type: cross Abstract: Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop.
arXiv AI
Jul 9
Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1
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.