Natasha Jaques

@natashajaques

Assistant Professor leading the Social RL Lab socialrl.cs.washington.edu @uwcse and Staff Research Scientist at @GoogleAI.

Seattle, WA

natashajaques.ai

Replies Reposts Media

Pinned
Natasha Jaques
@natashajaques
Aug 20
Recursive Self-Improvement through Multi-agent RL Post-training and Unsupervised Environment Design (UED)… but it actually works! Delighted to finally release this paper, which trains a single LLM to act as both an Environment Designer to build new multi-turn RL training
Bo Liu (Benjamin Liu)
@Benjamin_eecs
Aug 20
Continuous self-improvement needs an ever-expanding supply of training environments (goals). SPADE: one model self-plays the Environment Designer and the Reasoning Agent, writing executable, agentic environments that get harder as it improves. Environment scaling on its own. ♠️
00:00
13
Natasha Jaques
@natashajaques
Sep 15
LLMs give eerily similar responses to the same prompt, even across different model families. Ask it to name a “well-received book” 6 times, and it will name “To Kill a Mockingbird” every time. In this work, we propose a method to address this problem with multi-agent RL
Carrie Yuan 袁嘉仪
@carrieyuanjiayi
Sep 15
🧬 "In the course of evolution, nature has gone to endless trouble to see that every individual is unlike every other individual." Yet LLMs are forcing us all to be alike by giving us mode-collapsed, homogeneous responses. We propose a multi-agent RL method to fix this. 🧵
5
Natasha Jaques
@natashajaques
Sep 14
Gave a recent talk about this work, which you can check out here if you're interested: youtube.com/watch?v=brbZ3N…
Natasha Jaques
@natashajaques
Aug 20
Recursive Self-Improvement through Multi-agent RL Post-training and Unsupervised Environment Design (UED)… but it actually works! Delighted to finally release this paper, which trains a single LLM to act as both an Environment Designer to build new multi-turn RL training
Natasha Jaques
@natashajaques
Sep 12
No, RL post-training on random rewards does not improve model capabilities, except under very particular circumstances. Yes, RL post-training can teach models capabilities that aren’t already present in the base model’s pass@k distribution. While these findings might be obvious
Sankar Harilal
@sankar_harilal
Sep 12
Can RL post-training improve model capabilities with random rewards? And can it teach skills outside the base model's distribution? Our new paper, Demystifying Reinforcement Learning Post-training of Language Models, unpacks why it succeeds or fails. arxiv.org/abs/2608.24949 🧵
6
Natasha Jaques
@natashajaques
Sep 11
In a random soup of programs mutating over time, self-replicating programs will eventually come to dominate. But will they learn to cooperate with each other? In Kunal’s latest paper on Autopoietic Game Theory, we examine exactly this question. We set up a system in which
Kunal Jha
@kjha02
Sep 11
Can self-interested, self-improving, self-replicating agents learn to cooperate? Our new paper, Tapes Together Strong, shows they can: when social behavior, computation, and reproduction share one energy budget, cooperation evolves from scratch. arxiv.org/abs/2609.10817 🧵
GIF
5