Pinned Tweet
Introducing Reinforcement Learning from Collective Rewards (RLCR).
RLCR is a recipe that trains language models as agent organisations, which share a message board and workspace. We use it to train Avalon-M1-Mini (120B) and study its behaviour.
We find a number of interesting Learnt organisational hierarchies and divisions of labour
🕵️ Increased collective verification, through hires of verifiers and testers
👥 The rise of collective thinking, where agents think more about other agents and how to help them
We believe RLCR can provide a laboratory for studying collective intelligence and multi-agent safety.
Blog post and technical report 👇
RLCR is a recipe that trains language models as agent organisations, which share a message board and workspace. We use it to train Avalon-M1-Mini (120B) and study its behaviour.
We find a number of interesting Learnt organisational hierarchies and divisions of labour
🕵️ Increased collective verification, through hires of verifiers and testers
👥 The rise of collective thinking, where agents think more about other agents and how to help them
We believe RLCR can provide a laboratory for studying collective intelligence and multi-agent safety.
Blog post and technical report 👇
98
184
1,949
194,916
Hear the story of how we developed Avalon at the London AO Summit hosted by @ARIA_research.
We’ll be talking not only about the results, but the research process of how we got there, and what our future roadmap looks like.
We’ll be talking not only about the results, but the research process of how we got there, and what our future roadmap looks like.
More London AO Summit speakers!
+ @ChengxiTaylor of @GenReasoning on the first autonomous company model
+ @yalidux on safe cooperative AI
+ @brulepri on systemic risk in AI collectives
Nov 5–6, hosted by AO Commons and @ARIA_research Apply to attend: luma.com/j1lmnrxk
3
0
13
1,639
General Reasoning retweeted
General Reasoning CEO @rosstaylor90 explains how their new RLCR experiment taught AI agents to organize themselves, hire teammates, and decide when to DM each other:
"The idea of RLCR is, instead of just trying to optimize single agents, how do you optimize collective arch communities, and eventually economies, markets."
"We optimize an organization in a Slack-like harness. They learn who they should hire, what roles they should hire for, when they should be pinging someone annoyingly in their direct messages versus making a public channel."
"It’s not just another model, it’s a whole new ball game. It’s a whole new direction."
@GenReasoning
"The idea of RLCR is, instead of just trying to optimize single agents, how do you optimize collective arch communities, and eventually economies, markets."
"We optimize an organization in a Slack-like harness. They learn who they should hire, what roles they should hire for, when they should be pinging someone annoyingly in their direct messages versus making a public channel."
"It’s not just another model, it’s a whole new ball game. It’s a whole new direction."
@GenReasoning
Introducing Reinforcement Learning from Collective Rewards (RLCR).
RLCR is a recipe that trains language models as agent organisations, which share a message board and workspace. We use it to train Avalon-M1-Mini (120B) and study its behaviour.
We find a number of interesting Learnt organisational hierarchies and divisions of labour
🕵️ Increased collective verification, through hires of verifiers and testers
👥 The rise of collective thinking, where agents think more about other agents and how to help them
We believe RLCR can provide a laboratory for studying collective intelligence and multi-agent safety.
Blog post and technical report 👇
3
3
22
7,687
Read below for a summary of our findings and our technical report.
This is still under revision as we train Avalon-M1-Mini. We are a small team, so please be patient as we get back to you on any questions, or make updates.
gr.inc/releases/avalo…
This is still under revision as we train Avalon-M1-Mini. We are a small team, so please be patient as we get back to you on any questions, or make updates.
gr.inc/releases/avalo…
2
8
107
10,808
General Reasoning retweeted
@petergostev makes experiments way more reproducible, its a nice way to guarantee that solution on the live internet won’t leak your evals, and prevents hacking.
it’s not a big uplift if you already have your own search engine.
General Reasoning folks are even offering it as a service:
it’s not a big uplift if you already have your own search engine.
General Reasoning folks are even offering it as a service:
🔍 Introducing BackSearch.
LLMs are increasingly asked to predict the future, but a good backtest requires a snapshot of the internet at a point in time.
BackSearch allows LLMs to search the web as it was on a particular date. It’s great for:
🔮 Forecasting and prediction finance.
🌍 RL environments that simulate the world.
🥶 Freezing websearch for benchmark reproducibility
We’re releasing a narrow slice of our index to begin with, focused on the news domain for 2026. Based on feedback we’ll open up more of our index in subsequent releases.
👇 Try BackSearch out with the link below.
2
4
40
7,981
🔍 Introducing BackSearch.
LLMs are increasingly asked to predict the future, but a good backtest requires a snapshot of the internet at a point in time.
BackSearch allows LLMs to search the web as it was on a particular date. It’s great for:
🔮 Forecasting and prediction finance.
🌍 RL environments that simulate the world.
🥶 Freezing websearch for benchmark reproducibility
We’re releasing a narrow slice of our index to begin with, focused on the news domain for 2026. Based on feedback we’ll open up more of our index in subsequent releases.
👇 Try BackSearch out with the link below.
LLMs are increasingly asked to predict the future, but a good backtest requires a snapshot of the internet at a point in time.
BackSearch allows LLMs to search the web as it was on a particular date. It’s great for:
🔮 Forecasting and prediction finance.
🌍 RL environments that simulate the world.
🥶 Freezing websearch for benchmark reproducibility
We’re releasing a narrow slice of our index to begin with, focused on the news domain for 2026. Based on feedback we’ll open up more of our index in subsequent releases.
👇 Try BackSearch out with the link below.
74
153
2,232
421,804
Details on how to try BackSearch out here: gr.inc/releases/intro…
1
6
85
15,249
Major FutureSim updates!
🥽 Visualized trajectories: extremely long horizon, 1000s of actions per run and dozens of compactions, with summaries! Goldmine of interesting agent behaviors across Fable 5, GPT 5.5, GLM 5.2 etc!
📈 @OpenReward integration! You can now use FutureSim, with our favourite standard! The @GenReasoning was super supportive in making this happen!
Some cool observations in 🧵
1
3
17
5,166
We evaluated recent open models on KellyBench.
Here is what we found:
🏆 GLM 5.2 is new open source SoTA, but still loses -30% on average over 5 runs.
📈 We estimate GLM 5.2 is 6+ months behind the frontier based on KellyBench and internal quant evaluations. (Note: we have Kimi K2.6 slightly improves on Kimi K2.5 but still struggles at -60% average RoI.
🐈 Recent Mistral models struggle, obtaining mean RoIs of -78% and -99% respectively.
Leaderboard link and more graphs below.
Here is what we found:
🏆 GLM 5.2 is new open source SoTA, but still loses -30% on average over 5 runs.
📈 We estimate GLM 5.2 is 6+ months behind the frontier based on KellyBench and internal quant evaluations. (Note: we have Kimi K2.6 slightly improves on Kimi K2.5 but still struggles at -60% average RoI.
🐈 Recent Mistral models struggle, obtaining mean RoIs of -78% and -99% respectively.
Leaderboard link and more graphs below.
2
5
65
22,177
Because of backtest variance, we also record a process-based rubric measure called "sophistication", which we track over time. This uses a human expert rubric to judge the sophistication of the strategies employed.
GLM-5.2 shows impressive sophistication compared to other open ll does not surpass the closed SoTA on this metric for any time this year.
You can see the full leaderboard and more analysis here:
gr.inc/releases/intro…
GLM-5.2 shows impressive sophistication compared to other open ll does not surpass the closed SoTA on this metric for any time this year.
You can see the full leaderboard and more analysis here:
gr.inc/releases/intro…
0
0
12
2,932
New models on KellyBench, the benchmark for long-horizon sequential decision making.
🎆 Claude Opus 4.7 - new state-of-the-art, with the highest strategy sophistication recorded on the benchmark (28.5%). But still loses -3.7% on average over five seeds.
🐋 DeepSeek V4 Pro - velopment capabilities, but scores poorly on overfitting rubrics which harms it in deployment (-47%).
Link and more graphs below.
🎆 Claude Opus 4.7 - new state-of-the-art, with the highest strategy sophistication recorded on the benchmark (28.5%). But still loses -3.7% on average over five seeds.
🐋 DeepSeek V4 Pro - velopment capabilities, but scores poorly on overfitting rubrics which harms it in deployment (-47%).
Link and more graphs below.
2
5
92
12,050
We’re also thankful that KellyBench was featured on the front page of the FT last month!
(The British AI neuron has a superposition with football…)
(The British AI neuron has a superposition with football…)
1
0
4
991
We've updated the leaderboard with GPT-5.5 results:
gr.inc/releases/intro…
TLDR: 30% strategy sophistication (new SoTA), much more efficient than GPT-5.4, but still in the red and systematically underperforming human approaches.
gr.inc/releases/intro…
TLDR: 30% strategy sophistication (new SoTA), much more efficient than GPT-5.4, but still in the red and systematically underperforming human approaches.
0
0
1
581
🌍 Last month we hosted the Complex Worlds Hackathon in London.
Participants built an impressive range of environments, spanning synthetic game pipelines, arable farm management, dynamic vehicle routing, hospital triage, robotics, cybersecurity, and more.
Congrats to our d Khalid A!
Participants built an impressive range of environments, spanning synthetic game pipelines, arable farm management, dynamic vehicle routing, hospital triage, robotics, cybersecurity, and more.
Congrats to our d Khalid A!
3
4
30
6,155
Thanks to @ibragim_bad, Jeff Smith and Giovanni R for judging. Thanks to event partners @joinef @airstreet.
You can view the environments contributed at the event below:
openreward.ai/environments
You can view the environments contributed at the event below:
openreward.ai/environments
0
0
0
697
🎉 Native Harbor support on OpenReward!
🐋 Connect your GitHub repository. We'll build the Docker images for each harbor task and deploy the environment as an API endpoint.
🚂 Train on the deployed tasks with any RL framework.
⚖️ Evaluate on the deployed tasks with any harness.
Drop the anchor here and get started below:
docs.openreward.ai/environments/d…
🐋 Connect your GitHub repository. We'll build the Docker images for each harbor task and deploy the environment as an API endpoint.
🚂 Train on the deployed tasks with any RL framework.
⚖️ Evaluate on the deployed tasks with any harness.
Drop the anchor here and get started below:
docs.openreward.ai/environments/d…
0
6
25
4,999