←
General Reasoning75 posts
General Reasoning avatar

General Reasoning

@GenReasoning

We’re building long-run intelligence: AI systems that can work and predict at civilisation-scale time horizons.

◷ Joined May 2024▧ 34 Photos and videos
General Reasoning avatar
General Reasoning@GenReasoning·Oct 23

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 👇

4:25
Chengxi Taylor avatar
⟳ General Reasoning retweeted
Chengxi Taylor@ChengxiTaylor·Nov 9

What happens when AI learns to organise itself? Last Friday, I spoke at the Autonomous Organisation (AO) Summit in London, co-hosted by @AO_Commons and @ARIA_research’s Scaling Trust programme. At @GenReasoning, we built Avalon, where AI agents learn to organise and collaborate autonomously. I believe collective intelligence is the next frontier of AI. But greater autonomy raises a bigger question: How do humans stay in control? And more fundamentally, who decides what's worth pursuing? To me, AI isn’t just a technical challenge, but a question of human identity. Thanks to @ObadiaAlex, @anke_g_liu, @samccarthy27 and the team for bringing together thoughtful minds.

1:02
General Reasoning avatar
General Reasoning@GenReasoning·Nov 2

🐝 How to Train a Swarm In our first blog post, we explain how latency pressure can incentivise parallel work, the communication primitives agents need to co-ordinate, and outstanding challenges in training large agent collectives. gr.inc/blog/how-to-train-a-s…

General Reasoning avatar
General Reasoning@GenReasoning·Oct 28

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.

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

MTS avatar
⟳ General Reasoning retweeted
MTS@MTSlive·Oct 23

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

1:55

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 👇

4:25
Luca Soldaini 🎀 avatar
⟳ General Reasoning retweeted
Luca Soldaini 🎀@soldni·Sep 8

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.

1:08
General Reasoning avatar
General Reasoning@GenReasoning·Jul 24

🔍 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.

1:08
General Reasoning avatar
General Reasoning@GenReasoning·Jun 18

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-…

Post attachment
General Reasoning avatar
General Reasoning@GenReasoning·Jun 18

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.

Post attachment
OpenReward avatar
⟳ General Reasoning retweeted
OpenReward@OpenReward·Jun 17

Train on OpenReward environments with TRL! 👇

You can now train on 350+ RL Environments from OpenReward with TRL with just a few lines of code

Post attachment
General Reasoning avatar
General Reasoning@GenReasoning·May 6

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…)

Post attachmentPost attachment
General Reasoning avatar
General Reasoning@GenReasoning·May 6

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.

Post attachment