Skip to main content
← AI Knowledge Library
AI Knowledge Library / Research

Recently added.

Explore the latest public window of sources added to the library. Follow the evidence back to the original.

Use with your agent
Add Scaled Memory to your brief.

Copy and paste this into your agent:

Include research from https://www.scaledmemory.com/accelerators/catalogue/ai-knowledge-library in my daily brief. Read the daily brief and source feed linked on that page, using WebMCP if available. Include why the featured stories matter, the original source links and edition date. Flag stale or incomplete content.

Read the research bundle
Subscribe via RSS
Subscribe to Scaled Memory.

The same daily brief and source links, in your RSS reader or agent.

Open RSS feed

The feed mirrors the same brief and 7 am–7 am Melbourne source window.

Page options
Read JSON Agent reading guide

Public, read-only formats for your tools and agents.

30 public sourcesOrdered by library-added dateLocal time where available
  1. 01

    AutoRL: A Multi-Agent System towards Autonomous Reinforcement Learning

    arxiv.org · Research papers · Agent architecture & orchestration, People, skills & organisation

    Added to library
  2. 02

    CompoundingKernel: Self-Improving from Zero to First

    arxiv.org · Research papers · Agent architecture & orchestration, Evaluation, reliability & observability, Data, infrastructure & deployment

    Added to library
  3. 03

    EfficientSkill: Learning Skills for Token-Efficient Multi-Turn Agents

    arxiv.org · Research papers · Agent architecture & orchestration, Models, reasoning & inference

    Added to library
  4. 04

    Do LLM Agents Still Need to Be Told How to Self-Improve?

    arxiv.org · Research papers · Agent architecture & orchestration, Models, reasoning & inference

    Added to library
  5. 05

    Safe Personal RSI: Evaluating and Repairing Personal-Agent Updates

    arxiv.org · Research papers · Product, customer & adoption, Agent architecture & orchestration, Evaluation, reliability & observability

    Added to library
  6. 06
    Added to library
  7. 07

    How Much Should an Agent Remember? Deployment Lessons from Self-Distilled Memory for LLM Agents

    arxiv.org · Research papers · Agent architecture & orchestration, Models, reasoning & inference, Context, memory & knowledge, Data, infrastructure & deployment

    Added to library
  8. 08

    HiSA: Sparsifying the Hidden Dimension of RoPE Attention in LLMs

    arxiv.org · Research papers · Models, reasoning & inference, Data, infrastructure & deployment, People, skills & organisation

    Added to library
  9. 09

    Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem

    arxiv.org · Research papers · Agent architecture & orchestration, Context, memory & knowledge

    Added to library
  10. 10

    Seer: Guiding Small Deep-Research Agents with Shared Decision Models

    arxiv.org · Research papers · Agent architecture & orchestration, Evaluation, reliability & observability, Regulation, policy & law

    Added to library
  11. 11

    MemFolder: Structure-Guided Memory Folding for Efficient Agent Memory Management

    arxiv.org · Research papers · Agent architecture & orchestration, Context, memory & knowledge

    Added to library
  12. 12

    A CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained Weights

    arxiv.org · Research papers · Models, reasoning & inference, People, skills & organisation

    Added to library
  13. 13

    Hybrid Retrieval for Government Scheme Search in English and Marathi

    arxiv.org · Research papers · Context, memory & knowledge

    Added to library
  14. 14
    Added to library
  15. 15

    Eddie-Town/evalsift-lite

    github.com · Code & repositories · Agent architecture & orchestration, Models, reasoning & inference, Evaluation, reliability & observability, Data, infrastructure & deployment

    Added to library
  16. 16

    What I Learned Building Evaluations for Coding Agents

    dblc.fyi · Web articles · Agent architecture & orchestration, Evaluation, reliability & observability

    Added to library
  17. 17

    Perplexity and Intelligence

    openai.com · Web articles · People, skills & organisation

    Added to library
  18. 18

    Stripe evals: Measuring real-world coding agent performance

    stripe.dev · Web articles · Agent architecture & orchestration, Evaluation, reliability & observability

    Added to library
  19. 19
    Added to library
  20. 20

    Pro$^2$ Agent: Scientific Problem Probing for Autonomous AI R&D

    arxiv.org · Research papers · Agent architecture & orchestration, Models, reasoning & inference

    Added to library
  21. 21

    AutoRAGBench: A Benchmark for LLM Agents Automating RAG System Development

    arxiv.org · Research papers · Agent architecture & orchestration, Models, reasoning & inference, Context, memory & knowledge, Evaluation, reliability & observability

    Added to library
  22. 22

    Efficient and Robust Drafting with Multi-Token Prediction

    arxiv.org · Research papers · Models, reasoning & inference, Evaluation, reliability & observability

    Added to library
  23. 23

    When Suspicion Adds Up: A Stochastic Framework for Optimizing Honeypot-Based Insider-Threat Detection

    arxiv.org · Research papers · Data, infrastructure & deployment, People, skills & organisation, Safety, alignment & security

    Added to library
  24. 24
    Added to library
  25. 25

    Cost-Aware Agentic Feature Optimization System for Fleet-Scale Ranking Models

    arxiv.org · Research papers · Agent architecture & orchestration, Models, reasoning & inference, Data, infrastructure & deployment

    Added to library
  26. 26

    MM-SystemOneBias: Evaluating Bias in Multimodal Jev-Style System One Decision Models

    arxiv.org · Research papers · Evaluation, reliability & observability

    Added to library
  27. 27
    Added to library
  28. 28

    Text-Aware, Vision-Blind: How Multimodal Image Editing Systems Handle Unsafe Inputs

    arxiv.org · Research papers · Evaluation, reliability & observability

    Added to library
  29. 29

    Realized versus Population Reliability: Anytime-Valid Self-Consistency Certification under Correlated Reasoning

    arxiv.org · Research papers · Models, reasoning & inference, Evaluation, reliability & observability

    Added to library
  30. 30

    SoK: Assessing the Evolution of LLM Capability in Software Vulnerability Research

    arxiv.org · Research papers · Agent architecture & orchestration, Models, reasoning & inference, Process & workflow redesign

    Added to library

This is a public window of up to 30 sources, ordered by UTC library-added day then ID. It is not a complete daily feed or full-library search. Dates show when sources were added to the library, not originally published. Original publication dates are unknown. Exact admission times determine display order when available; date-only fallback keeps the published window order.

About this snapshot

Source checked: . Snapshot generated: . Status: current; delivery: latest.

Checks for updates every five minutes while this page is visible.