·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Apple Watch’s AI features for rewinding and recapping conversations begin beta testing1h◆Beyond Public Access in LLM Pre-Training Data3h◆M$^\star$: Every Task Deserves Its Own Memory Harness3h◆There Is No Free Loop: When Does Looping a Trained Model Pay for Its Inference Compute?3h◆Controllable User Simulation3h◆Latent-Lens: Visual Perception in Small Language Models Through Latent Communication3h◆Vision Transformer Ensembles for Panoramic Street Segmentation3h◆AI evaluators favor job applications written by certain AI models, independent of candidate quality3h◆Know When the Equation Is Wrong: Structural Uncertainty for LLM-Guided Symbolic Regression under Extrapolation3h◆Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control3h◆Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics3h◆Verification and Self-Improvement in Agentic AI: Foundations and Limits3h◆From Stages to States: Unified Iterative Reasoning for MLLMs3h◆MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs3h◆Specification-Aware Distribution Shaping for Robotics Foundation Models3h◆HyCO: A Hybrid Neural Solver for Combinatorial Optimization3h◆Learning and Transferring Closed-Loop Robot Software3h◆SparseGDN: Chunk Sparse in Linear Attention3h◆Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News3h◆FedPA-LoRA: Product-Aligned Framework for Mitigating Aggregation and Initialization Errors in Heterogeneous Federated LoRA3h◆Apple Watch’s AI features for rewinding and recapping conversations begin beta testing1h◆Beyond Public Access in LLM Pre-Training Data3h◆M$^\star$: Every Task Deserves Its Own Memory Harness3h◆There Is No Free Loop: When Does Looping a Trained Model Pay for Its Inference Compute?3h◆Controllable User Simulation3h◆Latent-Lens: Visual Perception in Small Language Models Through Latent Communication3h◆Vision Transformer Ensembles for Panoramic Street Segmentation3h◆AI evaluators favor job applications written by certain AI models, independent of candidate quality3h◆Know When the Equation Is Wrong: Structural Uncertainty for LLM-Guided Symbolic Regression under Extrapolation3h◆Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control3h◆Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics3h◆Verification and Self-Improvement in Agentic AI: Foundations and Limits3h◆From Stages to States: Unified Iterative Reasoning for MLLMs3h◆MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs3h◆Specification-Aware Distribution Shaping for Robotics Foundation Models3h◆HyCO: A Hybrid Neural Solver for Combinatorial Optimization3h◆Learning and Transferring Closed-Loop Robot Software3h◆SparseGDN: Chunk Sparse in Linear Attention3h◆Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News3h◆FedPA-LoRA: Product-Aligned Framework for Mitigating Aggregation and Initialization Errors in Heterogeneous Federated LoRA3h◆
News/What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md
arxiv
PublishedOctober 27, 2026 at 4:00 AM

What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2610.31715v2 Announce Type: replace-cross Abstract: Coding agents can be guided with instruction files in a repository. We examine this emerging practice through a census of 22,854 popular, active GitHub repositories in thirteen languages, treating each repository's root 'AGENTS$.$md' and 'CLA

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivBeyond Public Access in LLM Pre-Training Data3harxivM$^\star$: Every Task Deserves Its Own Memory Harness3harxivThere Is No Free Loop: When Does Looping a Trained Model Pay for Its Inference Compute?3harxivControllable User Simulation3h
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews