We worked with @trajectorylabs to run their SDPO++ algorithm on APEX-Agents and see what it could do with real production data. Pass rates went from 5% to 25% on GPT-OSS-120B, and the curve is still climbing.
Read more about our work together in their blog post below.
5 Days of Trajectory
🏹Day 5: Scaling SDPO to Agentic Tasks
Continual learning means you must train on data from production. But production gives you one example per task. A user makes a request once. You get one trajectory, not a batch.
However, current RL algorithms don't work that way, They need groups of tasks. By definition, that means you need some artificial environment to perform those rollouts in. But what if you don't?
SDPO is a promising route. It learns from a single trajectory, with no group required and failures still producing signal. The shape of the method matches the shape of production data.
But one fundamental problem remained. Every published SDPO work assumed fresh, on-policy rollouts. Agentic work cannot give you that. Trajectories run for an hour or more and arrive stale. On true agentic tasks, naive SDPO collapses.
We fixed it. We're the first to make SDPO work on agentic tasks.
On Mercor's APEX-Agents, with hour-long trajectories and near-zero base pass rates: 25% average reward, 5x over zero-shot. More importantly, it trains stably and the curve is still climbing.
Read more below.
🏹 5 Days of Trajectory.
Day 4 - Why We’re Building Trajectory
AI is the most capable software ever built.
You correct it.
You teach it what you want.
However, the next session starts, and the learning is gone.
This is deeply unnatural - nothing intelligent works this way.
Today, we’re sharing the thesis behind Trajectory:
- why continual learning is the next platform shift in AI
- why the primitive governing that shift is the trajectory
- our plan to move products from being shipped to being grown: first make the intelligence layer better, faster, and cheaper; then make it shapeable; finally, make it learn
Read more below⬇️
We’re taking a quick break for the 5 days of Trajectory, but wanted to take this time to say that we’ve been named to @Redpoint’s 2026 Infrared 100 as one of the companies shaping the future of AI infrastructure.
We're so grateful for the recognition so early in our journey, and want to congratulate the other awardees as well!
🏹5 Days of Trajectory.
Day 3 - An Open Source Training Stack for Continual Learning
Building the platform for continual learning requires both partnering with pioneering AI companies, as we showed on Day 2 with Harvey, and working toward frontier research, which we are highlighting today.
Continual learning means models that improve hourly from real production use. But with the size of frontier models, this becomes quite difficult. A Qwen-397b would need to spin up and tear down repeatedly across six GPU nodes, and that's valuable time gone.
Our contribution is Continual LoRA (C-LoRA): many lightweight adapters running at once on one shared base model. Our insight centers on where the parallelism lives: instead of splitting one giant job across nodes, we load-balance many small jobs over a single base.
The result: 2.81x experiment throughput over single-tenant training, with no regression on rewards.
We built this together, with @anyscalecompute, @NovaSkyAI, and generous support from @GoogleCloud and @GoogleStartups. We've open-sourced on SkyRL as one of the first multi-LoRA, RL training platforms, so that every team can get to continual learning faster.
We’re very excited to see what you build, please reach out!
This is a great read on post-training and open models.
@harvey & @trajectorylabs post-trained Nemotron 3 Super on complex legal tasks with some very impressive initial results. All with auditable weights, real security, and clear provenance.
We're partnering with @trajectorylabs to bring sovereign continual learning to legal AI with NVIDIA Nemotron models.
Continual learning allows agents to improve over time from feedback on their work: every redline refines the next draft.
Open-weight models offer full auditability and data sovereignty over legal agents.
Using Trajectory's platform, we post-trained NVIDIA Nemotron 3 Super on our Legal Agent Benchmark (LAB), measuring performance on 1,200+ complex end-to-end legal tasks across 24 practice areas.
Initial results show that a post-trained Nemotron 3 Super can match performance of closed-source frontier models.
This is just the start: we'll keep pushing the frontier with the more powerful Nemotron 3 Ultra when available.
Welcome to Day 2. Yesterday, we showed the broader work we're doing with the pioneers of continual learning.
Today we'd like to deep dive on one: how we post-trained an open model for legal work, in partnership with @Harvey.
We've built a platform where production data is the moat. Every correction, retry, and edit becomes signal you can post-train on, and the models are plug and play: customer's can drop in their model of choice, and improve from there.
Fields like legal and finance make those demands absolute, with hard security, sovereignty, and provenance requirements. That's why we post-trained @nvidia 's open-weight Nemotron 3 Super, on Harvey's LAB benchmark.
The results, in just hours: post-trained Nemotron 3 Super approaches the closed frontier, matches GPT 5.5, lifts rubric-pass criteria +25%, all while beating the performance-vs-cost frontier. That's the power of our platform.
And this is just a glimpse towards what the future of intelligence will look like: continual learning, where products get smarter every time they're used.
Thanks to @nikogrupen, @gabepereyra, @ItsJulioPereyra, and the whole Harvey team for their collaboration on this. Much more to come soon on continually learning legal agents
5 days of Trajectory begins today.
Today we are introducing the Pioneers of Continual Learning: some of the first companies building products that keep improving long after they ship.
This is how products will be built in the future, and we are building it together.
Read more about @harvey, @ClayRunHQ, @DecagonAI, and @mercor_ai in our blog post below.
5 days.
5 announcements.
5 days of Trajectory starts today.
Yesterday we launched Trajectory (@trajectorylabs). We are building the platform for Continual Learning.
Our platform unlocks the signal already sitting in product usage, so companies can continuously post-train large agentic models that outperform the frontier.
Today we are introducing the Pioneers of Continual Learning: some of the first companies building products that keep improving long after they ship. This is how products will be built in the future, and we are building it together.
Here, we’d love to highlight a few of these companies:
—
@harvey is pushing the frontier of legal AI, in a domain that has little tolerance for mistakes. They’ve turned this standard into LAB, an open, expert-graded benchmark. Now, with Trajectory, they are building on that signal toward models that continually improve.
@ClayRunHQ has built go-to-market to be AI-native from first principles, and now with Trajectory, they're A/B testing models live that are already cheaper, faster, and most importantly, continually learning.
@DecagonAI runs most of their agents on models they trained themselves. Together with Trajectory, they are now exploring how to train models with special capabilties (steerability, interpretability) that owning your own intelligence unlocks, all with the goal of continually improving in production.
@mercor_ai is the expert layer beneath frontier AI, turning the judgment of professionals across law, banking, and consulting into benchmarks that grade agents against real work. They are now working with Trajectory on how continual learning can unify model training and the data generation process.
—
We believe AI should compound, not stagnate. That's the future we're building with the Pioneers of Continual Learning. Read the full story in the blog post below.
Today, @MichaelElabd, @QuantumArjun, and I are excited to announce Trajectory.
We are a research lab and product company building the platform for Continual Learning.
Our platform unlocks the signal already sitting in product usage, so companies can continuously post-train large-scale agentic models that outperform the frontier. @trajectorylabs
We’ve raised $15M from @Conviction, @BessemerVP, @radicalvcfund, @jeffdean, @drfeifei and more.
We’re partnering with some of the best AI-native companies: @ClayRunHQ@Harvey, @DecagonAI, @mercor_ai, @RogoAI to power their agentic systems, some of which we are already in production with.
We’ve brought together a world class research team from DeepMind, OpenAI, Apple, Meta Superintelligence, Amazon AGI, Scale AI, and an elite product team from Stripe and Figma.
AI will never again start on day one. Every correction, every retry, every edit will make products smarter. This is Continual Learning.