🇰🇷 한국어

• [Paper Review] ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence

  Papers from autonomous research agents read well but their evidence chains are broken. An audit of 75 papers exposes a systematic failure in every baseline, and a system that keeps every claim tied to its evidence while writing.

  56 min read   ·   August 04, 2026

  2026   ·   autonomous-research   llm-agents   verifiability   hallucination   evaluation   ai-scientist   ·   paper-review

  

• [Paper Review] Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

  Four atomic operators — Draft, Improve, Debug, Crossover — shared between post-training and evolutionary search. A 35B model hits 71.21% on MLE-Bench Lite on a single RTX 4090 with a 12-hour per-task budget.

  46 min read   ·   August 03, 2026

  2026   ·   ai4ai   recursive-self-improvement   mle-agent   evolutionary-search   reinforcement-learning   post-training   agent   ·   paper-review

  

• [Paper Review] Kimi K3: Open Frontier Intelligence

  A 2.8T-parameter, 104B-active, 1M-context open-weight MoE. Kimi Delta Attention, Attention Residuals, and Stable LatentMoE push scaling efficiency 2.5x over Kimi K2 to reach the frontier.

  34 min read   ·   July 31, 2026

  2026   ·   mixture-of-experts   linear-attention   long-context   reinforcement-learning   multimodal   open-weights   llm-infrastructure   ·   paper-review

  

• [Paper Review] Autodata: An agentic data scientist to create high quality synthetic data

  An LLM agent that acts as a data scientist — creating synthetic data, evaluating it, and revising its recipe in a loop — plus how to meta-optimize the agent itself.

  29 min read   ·   June 29, 2026

  2026   ·   synthetic-data   llm-agents   self-instruct   reinforcement-learning   grpo   data-generation   ·   paper-review

  

• [Paper Review] SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attacks

  Turning detection failures into knowledge — SHIELD pairs a three-stage defense pipeline with a knowledge-update and prompt-optimization loop to self-heal against sponge attacks.

  24 min read   ·   June 25, 2026

  2026   ·   sponge-attack   llm-security   denial-of-service   agentic-defense   prompt-optimization   ·   paper-review

  

• [Paper Review] Code World Model Preparedness Report

  Meta's pre-release frontier-risk assessment of CWM, a 32B open-weight code model, across cybersecurity, chemical & biological, and honesty (propensity) domains.

  23 min read   ·   June 25, 2026

  2026   ·   ai-safety   frontier-risk   llm-evaluation   cybersecurity   biosecurity   honesty   ·   paper-review

  

• [Paper Review] A Survey on Generative Recommendation: Data, Model, and Tasks

  A survey that reframes recommendation from discriminative scoring to generative synthesis, organized along the data, model, and task axes

  25 min read   ·   June 04, 2026

  2026   ·   generative-recommendation   large-language-models   diffusion-models   recommender-systems   survey   ·   paper-review

  

• [Paper Review] Multi-Interest Recommendation: A Survey

  The first comprehensive survey of multi-interest recommendation, organizing the field around extractors, aggregators, diversity regularization, applications, and open challenges.

  23 min read   ·   June 04, 2026

  2026   ·   recommender-systems   multi-interest   sequential-recommendation   survey   user-modeling   ·   paper-review

  

• [Paper Review] Robust Uplift Modeling with Large-Scale Contexts for Real-time Marketing

  A review of UMLC (KDD 2025): a model-agnostic uplift framework that tames the distribution shift and variance inflation caused by large-scale contexts via response-guided context grouping and feature interaction.

  24 min read   ·   June 01, 2026

  2026   ·   uplift-modeling   causal-inference   treatment-effect   real-time-marketing   recommender-systems   representation-learning   ·   paper-review

  

• [Paper Review] Personalization and targeting: how to experiment, learn & optimize

  An IJRM review that formalizes personalization as a causal-inference problem and walks through the test-and-learn cycle for experimenting, learning, and optimizing

  23 min read   ·   June 01, 2026

  2026   ·   personalization   causal-inference   machine-learning   marketing   targeting   experimentation   ·   paper-review