Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Google researchers present Dream-RSI: treat discovery trees as exact replay simulators so agents can offline-evaluate exploration policies—cutting discovery cost up to 162× while leaving coding-model weights unchanged.

Research · AI Agents · Research · Machine Learning · AI

Training a 4B model to produce 81% faster query plans than Postgres

Leis et al. asked this exact question in 2015. Then, they asked it again 10 years later. Despite an enormous body of research spanning a decade since their original exploration, they found that query optimizers continue to leave much to be desired. I was surprised when I first learned about this. A Postgres database should know everything about the stuff that lives in its tables, no? How hard can it be?

Research · AI · Machine Learning · Performance · Databases

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

Tagliabue, Dung, and Berg identify a linear “pain axis” in 25 open-weight models that responds to self-directed harm and steers models toward relief—even when that costs the user—sparking debate on functional signatures vs sentience.

Research · AI · LLMs · Research · AI Safety

Why machine learning research agents don't overfit — and what compression has to do with itNew research indicates that AI agents learn compressible models of data, which don't have enough space to enable memorization.

Amazon Science researchers explain why ML research agents fail to overfit benchmarks even after many evaluation rounds, arguing that successful agents learn highly compressible representations that are too compact to store memorised answers — connecting this to Minimum Description Length theory.

Research · Machine Learning · AI Agents · Benchmarks · Research

The Implications of Linguistic Illegibility for LLM Security

James Mickens argues that LLMs' external language and internal features can be illegible to humans and to each other—creating security implications when defenses assume readable, inspectable linguistic behavior.

Research · Security · LLMs · AI Safety · Research

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Frontis.AI / Horizon Research open-source OpenMLE (gym, RL, Evo) and Frontis-MA1-35B, lifting MLE-Bench Lite medal average to 71.21% under a single RTX 4090 budget toward executable RSI research.

Research · Machine Learning · Research · AI Agents · Open Source

Continuous diffusion language models

A flurry of recent activity in the space of continuous diffusion models for language, after a few years of relative dormancy, suggests that this approach is making something of a comeback. Fully discrete diffusion methods had largely supplanted earlier attempts to make continuous diffusion work for language, but the tide is starting to turn. In this post, I want to take a closer look at what’s going on, and why it is happening now. The recent influx of new research in this…

Research · AI · LLMs · Machine Learning · Research

Sparse Reward Subsystem in Large Language Models

Guowei Xu, Mert Yuksekgonul, and James Zou report a sparse reward subsystem in LLM hidden states: value neurons encode expected value, while dopamine neurons track reward-prediction error. The study finds these signals are robust across tasks and models and useful for confidence estimation and inference-time search.

Research · Research · Machine Learning · LLMs · AI

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Fu et al. propose Cache-to-Cache (C2C): multi-LLM systems exchange KV-cache semantics directly instead of text tokens, aiming for richer inter-model communication with lower latency and token cost.

Research · LLMs · Research · Machine Learning · AI