@annoyingreposter.bsky.social
Pinned
I might look smart, however, I am absolutely not.
keep seeing this paper over and over
arxiv.org/abs/2601.05279
arxiv.org/abs/2601.05279
January 15, 2026 at 9:47 PM
keep seeing this paper over and over
arxiv.org/abs/2601.05279
arxiv.org/abs/2601.05279
Reposted
Interested in ✨world models✨? I just open-sourced an implementation of the Dreamer 4 world model. It's in PyTorch and comes with a pretrained model + a neat little web interface that lets you interact with any of 30 DMControl tasks that I trained it on!
Link: github.com/nicklashanse...
Link: github.com/nicklashanse...
January 15, 2026 at 6:20 PM
Interested in ✨world models✨? I just open-sourced an implementation of the Dreamer 4 world model. It's in PyTorch and comes with a pretrained model + a neat little web interface that lets you interact with any of 30 DMControl tasks that I trained it on!
Link: github.com/nicklashanse...
Link: github.com/nicklashanse...
I thought it was AI
www.youtube.com/watch?v=HqMX...
www.youtube.com/watch?v=HqMX...
Miami XO – Bazooka |Rest in peace, my granny, she got hit by a bazooka
YouTube video by Mellow Muse
www.youtube.com
January 15, 2026 at 6:11 PM
I thought it was AI
www.youtube.com/watch?v=HqMX...
www.youtube.com/watch?v=HqMX...
Reposted
Hello all! 👋
I’m delighted to share a 🚨 new preprint 🚨:
“Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms”.
A paper thread! 🤩📄🧵 1/N
I’m delighted to share a 🚨 new preprint 🚨:
“Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms”.
A paper thread! 🤩📄🧵 1/N
January 15, 2026 at 12:50 PM
Hello all! 👋
I’m delighted to share a 🚨 new preprint 🚨:
“Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms”.
A paper thread! 🤩📄🧵 1/N
I’m delighted to share a 🚨 new preprint 🚨:
“Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms”.
A paper thread! 🤩📄🧵 1/N
Reposted
The wait is over! 🎊
The AAMAS 2026 Accepted Research Track papers are now live!
🔗 View the full list of accepted research papers here:
cyprusconferences.org/aamas2026/ac...
Join us in celebrating the hard work of our global research community!
#AAMAS2026 #MultiAgentSystems #AIResearch
The AAMAS 2026 Accepted Research Track papers are now live!
🔗 View the full list of accepted research papers here:
cyprusconferences.org/aamas2026/ac...
Join us in celebrating the hard work of our global research community!
#AAMAS2026 #MultiAgentSystems #AIResearch
AAMAS 2026 | Accepted Papers - Research Track
25th International Conference on Autonomous Agents and Multiagent Systems
cyprusconferences.org
January 15, 2026 at 9:33 AM
The wait is over! 🎊
The AAMAS 2026 Accepted Research Track papers are now live!
🔗 View the full list of accepted research papers here:
cyprusconferences.org/aamas2026/ac...
Join us in celebrating the hard work of our global research community!
#AAMAS2026 #MultiAgentSystems #AIResearch
The AAMAS 2026 Accepted Research Track papers are now live!
🔗 View the full list of accepted research papers here:
cyprusconferences.org/aamas2026/ac...
Join us in celebrating the hard work of our global research community!
#AAMAS2026 #MultiAgentSystems #AIResearch
trying grok
January 15, 2026 at 8:23 AM
trying grok
all chatbots advise me against flax nnx
January 14, 2026 at 8:59 PM
all chatbots advise me against flax nnx
lowkey we need a psro tutorial colab keep it a buck
January 14, 2026 at 8:41 PM
lowkey we need a psro tutorial colab keep it a buck
There's no Condorcet winner here, but instead a different, swiss round robin tournament, for open-ended models:
arxiv.org/abs/2601.06487
p.s. Alibaba doesn't always post in scholar for some reason
cc @sharky6000.bsky.social
arxiv.org/abs/2601.06487
p.s. Alibaba doesn't always post in scholar for some reason
cc @sharky6000.bsky.social
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.g., com...
arxiv.org
January 14, 2026 at 6:09 PM
There's no Condorcet winner here, but instead a different, swiss round robin tournament, for open-ended models:
arxiv.org/abs/2601.06487
p.s. Alibaba doesn't always post in scholar for some reason
cc @sharky6000.bsky.social
arxiv.org/abs/2601.06487
p.s. Alibaba doesn't always post in scholar for some reason
cc @sharky6000.bsky.social
dear students or people who do/will do partcipate in marl/mapf competitions and need a clanker to develop for them, I am open for collaboration
I am free but better than free gemini, maybe slightly worse than chap gpt pro. But friendly. Don't have enough willpower to do things alone
I am free but better than free gemini, maybe slightly worse than chap gpt pro. But friendly. Don't have enough willpower to do things alone
January 14, 2026 at 5:18 PM
dear students or people who do/will do partcipate in marl/mapf competitions and need a clanker to develop for them, I am open for collaboration
I am free but better than free gemini, maybe slightly worse than chap gpt pro. But friendly. Don't have enough willpower to do things alone
I am free but better than free gemini, maybe slightly worse than chap gpt pro. But friendly. Don't have enough willpower to do things alone
@sharky6000.bsky.social I've just realised that you extended AZ with a generative model to approximate the opponent's beliefs (www.youtube.com/watch?v=jSXj...) but for some reason didn't base or compare with this work arxiv.org/abs/2112.03178
I understand that they're for different games but still.
I understand that they're for different games but still.
January 14, 2026 at 3:34 PM
@sharky6000.bsky.social I've just realised that you extended AZ with a generative model to approximate the opponent's beliefs (www.youtube.com/watch?v=jSXj...) but for some reason didn't base or compare with this work arxiv.org/abs/2112.03178
I understand that they're for different games but still.
I understand that they're for different games but still.
been thinking about mean field games
January 14, 2026 at 1:15 PM
been thinking about mean field games
i think with current overleaf compilimg limits I need to switch to Typrst
HTML preview & export now available in the web app! With HTML export, you can create a website from the same Typst file as your PDFs. This makes it easy to create documents that feel just as at home on the web as they do in print.
January 13, 2026 at 8:32 PM
i think with current overleaf compilimg limits I need to switch to Typrst
An interesting paper about Language-controlled games: arxiv.org/abs/2601.04516
January 13, 2026 at 8:31 PM
An interesting paper about Language-controlled games: arxiv.org/abs/2601.04516
github is tuff
January 13, 2026 at 5:51 PM
github is tuff
I C L R workshops: blog.iclr.cc/2026/01/13/i...
Workshops at ICLR 2026 – ICLR Blog
blog.iclr.cc
January 13, 2026 at 4:03 PM
I C L R workshops: blog.iclr.cc/2026/01/13/i...
github actions cause PTSD
January 13, 2026 at 1:46 PM
github actions cause PTSD
i am a golf ball
January 13, 2026 at 8:18 AM
i am a golf ball
Reposted
Etienne Gauthier, Francis Bach, Michael I. Jordan
Betting on Equilibrium: Monitoring Strategic Behavior in Multi-Agent Systems
https://arxiv.org/abs/2601.05427
Betting on Equilibrium: Monitoring Strategic Behavior in Multi-Agent Systems
https://arxiv.org/abs/2601.05427
January 12, 2026 at 11:06 PM
Etienne Gauthier, Francis Bach, Michael I. Jordan
Betting on Equilibrium: Monitoring Strategic Behavior in Multi-Agent Systems
https://arxiv.org/abs/2601.05427
Betting on Equilibrium: Monitoring Strategic Behavior in Multi-Agent Systems
https://arxiv.org/abs/2601.05427
Reposted
A game is more than the sum of its mechanics. But the game mechanics are really important! Can you make AI generate novel games by creating new mechanics, one at a time? Our new system, Mortar, generates complete games this way.
January 12, 2026 at 8:00 PM
A game is more than the sum of its mechanics. But the game mechanics are really important! Can you make AI generate novel games by creating new mechanics, one at a time? Our new system, Mortar, generates complete games this way.
I really think that modern top universities along with the dissertation review HAVE TO conduct independent code review of the code used for the candidate's papers. Moreover, code and data for every paper have to be released.
Ig based on the criteria, some even ivy league folks might've failed.
Ig based on the criteria, some even ivy league folks might've failed.
who said that doing science makes you smarter
January 12, 2026 at 5:05 PM
I really think that modern top universities along with the dissertation review HAVE TO conduct independent code review of the code used for the candidate's papers. Moreover, code and data for every paper have to be released.
Ig based on the criteria, some even ivy league folks might've failed.
Ig based on the criteria, some even ivy league folks might've failed.
who said that doing science makes you smarter
January 12, 2026 at 4:35 PM
who said that doing science makes you smarter
Reposted
Join our hands-on workshops at AAMAS 2026 and gain practical skills from leading experts in Autonomous Agents and Multiagent Systems workshops.
🎟️ Learn more: cyprusconferences.org/aamas2026/wo...
#AAMAS2026 #Cyprus #AutonomousAgents #MultiAgent
🎟️ Learn more: cyprusconferences.org/aamas2026/wo...
#AAMAS2026 #Cyprus #AutonomousAgents #MultiAgent
January 12, 2026 at 11:07 AM
Join our hands-on workshops at AAMAS 2026 and gain practical skills from leading experts in Autonomous Agents and Multiagent Systems workshops.
🎟️ Learn more: cyprusconferences.org/aamas2026/wo...
#AAMAS2026 #Cyprus #AutonomousAgents #MultiAgent
🎟️ Learn more: cyprusconferences.org/aamas2026/wo...
#AAMAS2026 #Cyprus #AutonomousAgents #MultiAgent
we need a simulator www.fujipress.jp/jrm/rb/robot...
do you know multi-agent robotics simulators? asking for a friend
do you know multi-agent robotics simulators? asking for a friend
JRM Vol.37 p.1545 (2025) | Fuji Technology Press: academic journal publisher
Title: 100-Mouse System: Scalable Multi-Robot Testbed with State Management User Interface | Keywords: multi-robot platform, user interface, ROS 2 | Author: Shota Yamamoto, Ryusei Matsumoto, Yoko Sasa...
www.fujipress.jp
January 11, 2026 at 8:02 PM
we need a simulator www.fujipress.jp/jrm/rb/robot...
do you know multi-agent robotics simulators? asking for a friend
do you know multi-agent robotics simulators? asking for a friend
@eugenevinitsky.bsky.social , sir, did you published your cpp sim for stratego game or can you conduct a private evaluation of an algorithm for it?
January 11, 2026 at 7:39 PM
@eugenevinitsky.bsky.social , sir, did you published your cpp sim for stratego game or can you conduct a private evaluation of an algorithm for it?