paper

QueryBrew is a proposed system-agnostic approach for optimizing SQL-to-SQL queries, aiming to improve performance across different database systems.

This paper proposes a four-level framework classifying agentic visual generation systems based on the controller's direct decision scope over generation operations, from fixed support to experience-adaptive control.

A research paper titled 'Long Gaps' by Professor Jared Duker Lichtman of Stanford is hosted on OpenAI's platform, suggesting a focus on mathematical aspects in AI research.

A tweet from @cyrilXBT praises a paper on graph engineering for agentic systems, claiming it significantly improves AI responses, and promotes a spammy bidding website called RankNow.

TAMP-Nav is a unified framework that enhances embodied navigation by aligning vision-language models with 2D visual prompting, selective reasoning with compressed memory, and policy optimization, achieving state-of-the-art performance with high runtime and sample efficiency.

In this YC Design Review episode, Stephen Haney demonstrates Paper's agent-first AI workflow for designers, covering common AI design tells and how to avoid generic-looking output.

Anthropic releases technical papers detailing attacks on HAWK and AES encryption, including model chain-of-thought for AES.

CORVUS proposes a new trajectory architecture for LLM coding agents that decouples file-read actions from observations by maintaining a synchronized registry of relevant files, reducing input tokens by 9-50% and reasoning cycles by up to 37% while maintaining comparable pass rates on SWE-bench benchmarks.

Yohei Nakajima announces his first arXiv paper on event-sourced reactive graphs for auditable, forkable agentic systems, connecting graphRAG, DAG workflows, and log/trace graphs.

Introduces Distilled Reinforcement Learning, a method that uses a teacher model to provide fine-grained token-level gradient signals for LLM post-training, combining reinforcement learning with knowledge distillation.

A paper on few queries has been accepted at the ICML DL4C workshop.

A new paper introduces Graph Memory for LLM agents.

Tsinghua team proposes EurekAgent, arguing that the bottleneck in autonomous scientific research is environment engineering rather than smarter Agents. By engineering four dimensions—permissions, artifacts, budgets, and human-AI collaboration—they achieve SOTA on several mathematical and kernel engineering tasks, discovering a new optimal arrangement for 26 circles for under $11.

RepWAM introduces a world action modeling approach using representation visual-action tokenizers, aiming to learn unified visual and action representations for planning and control.

A Wharton paper concludes that AI must increase productivity by 2.7x quickly, or tech companies risk bankruptcy, with implications for the economy.

The article discusses surprising robustness of model distillation with respect to training distribution, even with little overlap with target distribution, and its implications for on/off-policy distillation.

Paper2Any is an open-source project that automatically generates academic materials such as model architecture diagrams, PPT presentations, and experiment charts from paper PDFs, screenshots, or text. It supports editing and one-click Docker deployment.

This paper provides a comprehensive compliance architecture for AI providers under EU law, focusing on agentic AI regulation. It is recommended by the AI Ethics Paper Club for developers and deployers navigating EU compliance.

A tweet recommending a paper that is described as the bible of distributed inference.

Yohei Nakajima published his first arXiv paper, "The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems", introducing a method for agents to coordinate through persistent replayable state.