We’re building long-run intelligence: AI systems that can work and predict at civilisation-scale time horizons.
London, England
Joined May 2024
- Tweets77
- Following3
- Followers8.1K
- Likes393
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 structures? Teams, research 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 results, including:
🛠️ 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 👇
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/avalon-m1
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 results, including:
🛠️ 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 👇
General Reasoning retweeted
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:
🔍 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 markets.
📈 Quantitative 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.
Details on how to try BackSearch out here: gr.inc/releases/introducing-…
🔍 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 markets.
📈 Quantitative 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.
OpenReward integration for FutureSim by @ShashwatGoel7 and team!
👇 Try it it out
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, incl. on your own data, with our favourite standard! The @GenReasoning was super supportive in making this happen!
Some cool observations in 🧵
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 models, although it still 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/introducing-…
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 not evaluated Fable)
🌗 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.
We've updated the leaderboard with GPT-5.5 results:
gr.inc/releases/introducing-…
TLDR: 30% strategy sophistication (new SoTA), much more efficient than GPT-5.4, but still in the red and systematically underperforming human approaches.
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…)
KellyBench is also now available as an arXiv preprint.
We'll continue to evaluate new models this year as they come in.
arxiv.org/abs/2604.27865
Link here: gr.inc/releases/introducing-…
We observe a positive trend in the quality of model strategies, but still weak saturation overall and systematic underperformance compared to human approaches.
(Note: we impose no time limits for models to develop strategies; they can use as much inference compute as they see fit)
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 - shows strong feature development capabilities, but scores poorly on overfitting rubrics which harms it in deployment (-47%).
Link and more graphs below.
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
🌍 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 winners, Julie Huang and Khalid A!
Hey @ruffy0369 - the SDK you are using is outdated; please upgrade to 1.101.
pypi.org/project/openreward/
🎉 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/environme…
