arXiv:2608. 05207v1 Announce Type: new Abstract: Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning.
arXiv:2608. 02712v1 Announce Type: cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness through pipelines that couple LLMs with agentic reinforcement learning and evolutionary search.
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.
arXiv:2607. 19386v1 Announce Type: new Abstract: Cross-paper comparison of sparse autoencoder (SAE) interpretability often relies on autointerpretability scores.
arXiv:2602. 02138v3 Announce Type: replace-cross Abstract: Despite the remarkable success that Multi-Agent Code Generation Systems (MACGS) have achieved, the inherent complexity of multi-agent architectures produces substantial volumes of intermediate outputs.
arXiv:2606. 18733v1 Announce Type: cross Abstract: Realistic coding-agent benchmarks often replay public GitHub issues and pull requests, making them vulnerable to overlap with model pretraining, fine-tuning, synthetic-data generation, or benchmark-driven model selection.
arXiv:2607. 01548v1 Announce Type: cross Abstract: Large language models are increasingly used as open-ended search operators in evolutionary optimization.
Real-world time-series forecasting is rarely a one-shot model invocation: practitioners must formulate tasks, connect data and models, incorporate domain expertise, assess prediction plausibility, and...
Large language models are increasingly used as open-ended search operators in evolutionary optimization. We introduce Evolutionary Feature Engineering (EFE), a framework for using LLM-based evolution to discover preprocessing transformations for structured data.
arXiv:2608.30976v1 Announce Type: new Abstract: Real-world time-series forecasting is rarely a one-shot model invocation: practitioners must formulate tasks, connect data and models, incorporate doma...
The paper introduces SAEScientist-Bench, a benchmark that tests whether AI agents can autonomously conduct mechanistic interpretability research using Sparse Autoencoders (SAEs). Agents are tasked with designing contrastive probes and navigating a large feature dictionary in Gemma-2-9B-IT to identify optimal features for a target concept, with performance measured against expert-curated references on activation rank, concept selectivity, and causal steering. Results show that while frontier agents can discover features and outperform controls, they still lag behind expert baselines, especially in causal steering, highlighting both the potential and current limitations of closed-loop autonomous AI research.
arXiv:2605. 06890v3 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control.
arXiv:2609.24862v1 Announce Type: new Abstract: Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning s...