Archive - Friendly Paper Review

or, Open Source SOTA

Sep 7 • Tim Dingman

August 2026

Memory in the Age of AI Agents: A Survey

or, It’s Not Just RAG!

Aug 31 • Tim Dingman

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

or, Tools All the Way Down

Aug 24 • Tim Dingman

Kimi K2.5: Visual Agentic Intelligence

or, How to Train Your Agent Swarm

Aug 17 • Tim Dingman

Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction

or, Why Siri and Alexa Failed

Aug 10 • Tim Dingman

Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments

or, How To Evaluate Your Agent

Aug 3 • Tim Dingman

July 2026

Reinforcement Learning via Self-Distillation

or, The Student Becomes the Master

Jul 27 • Tim Dingman

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

or, Learning to Learn From Experience

Jul 22 • Tim Dingman

RLAnything + OpenClaw-RL

Originally presented as a live talk on March 25, 2026

Jul 20 • Tim Dingman

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

or, Diffusion in Production

Jul 17 • Tim Dingman

mHC vs Attention Residuals

Originally presented as a live talk on April 1, 2026

Jul 13 • Tim Dingman

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

or, The Year of CUA

Jul 8 • Tim Dingman

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts