OpenReward

where machines get reward

[OpenReward @OpenReward]

We’re experiencing a brief environment outage due to a GCP degradation. Please bear with us - thank you!

[Nikhil Chandak @ COLM'26 @nikhilchandak29]

FutureSim is now supported in @OpenReward! Thanks to @GenReasoning for supporting reliable search with date cutoffs.

You can test your favorite model + scaffold on it. You can also bring your own data and replay it in our FutureSim environment and see how agents perform!

[General Reasoning @GenReasoning]

🔍 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.

[General Reasoning @GenReasoning]

OpenReward integration for FutureSim by @ShashwatGoel7 and team!

👇 Try it it out

[OpenReward @OpenReward]

Train on OpenReward environments with TRL! 👇

[Adithya S K @adithya_s_k]

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

[Quentin Gallouédec @QGallouedec]

TRL v1.4 is out! two things I'm excited about:

→ chunked NLL loss for SFT. Way less VRAM, same loss, often faster. Qwen3-14B @ 16k seq: 58.9 → 38.9 GB.
→ first-class @OpenReward integration. One line wires up an env into GRPO.
Plus: more chat templates, MFU helpers...

[Xiangyi Li @xdotli]

SkillsBench is now among the top environments on @OpenReward with 32k tool calls!

[Ai2 @allen_ai]

We built AstaBench to give the field a shared, transparent way to measure whether AI can do rigorous scientific work.

We’re pleased to see adoption with the @AISecurityInst via Inspect Evals and @GenReasoning, which added an AstaBench task to OpenReward.

[OpenReward @OpenReward]

🧪 We’re experimenting with new features that allow for easier sampling with popular agentic harnesses.

Core use cases:

- Collecting diverse agentic midtraining data
- Evaluating the latest models on agentic environments

Try it out!

[OpenReward @OpenReward]

Try it out on OpenReward:

https://t.co/z0YRHE6nYl

[General Reasoning @GenReasoning]

🎲 Introducing KellyBench, a new long-horizon evaluation for frontier models.

KellyBench evaluates models within a year long sports betting market, a challenging and highly non-stationary environment.

Every frontier model we test loses money. They struggle to design ML strategies, manage risk, and adapt as the world changes.

Link and thread below.

[OpenReward @OpenReward]

You can now train on OpenReward environments with SkyRL! Amazing work by @tyfeng1997 🙇

[Ty Feng @tyfeng1997]

Recently, I integrated @OpenReward into SkyRL (@NovaSkyAI), including an example demonstrating training with @modal. To verify the code, I ran several experiments—which proved to be a highly enriching experience! 😋
https://t.co/4zyGhp08ZY

[ƬⲘ @tm23twt]

timelapse 27 :)

- submitted the rust reasoning algo env to meta rl hack, (actually built a python then moved to the rust one) created rust dataset around 1000 problems will make it next to 2.5k
- define the whole reward logic not the optimal i think designed the way validation works, will refine it & push to @PrimeIntellect & @OpenReward envs.
- have some other tasks as well, deadline is Tomorrow so need to finish this
- this week was a pretty rough like peak locked in, so will chill & and just relax for few days

[OpenReward @OpenReward]

Claude Mythos Preview on SWE-Bench Pro appears to be a step change.

[OpenReward @OpenReward]

Congrats to @Zai_org team, new SOTA on SWE-Bench Pro!

https://t.co/wrFdHEXiMZ

[Z.ai @Zai_org]

Introducing GLM-5.1: The Next Level of Open Source

- Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo.
- Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations.

Blog: https://t.co/hmyDe4Nel3
Weights: https://t.co/CuUjXcPKJD
API: https://t.co/fz6reja4fb
Coding Plan: https://t.co/Nk8Y98HNhU

Coming to https://t.co/WCqWT0qCQb in the next few days.

[Parshin Shojaee @ParshinShojaee]

great to see our llm-srbench featured in openreward!

super exciting collection of science environments for agents!!

[General Reasoning @GenReasoning]

🌍 Environments of the Week

The theme this week...environments for science 👩‍🔬.

First up, LLM-SR Bench by @ParshinShojaee et al is an environment for evaluating language model agents on scientific equation discovery tasks.

https://t.co/zzx4Hv46LS

[Dimitris Papailiopoulos @DimitrisPapail]

@gandhikanishk's Endless Terminals is the most popular env on OpenReward!

[General Reasoning @GenReasoning]

🌍 Environments of the Week

It's been a week since we launched @OpenReward. Here are some of our favourite environments this week - some newly added, some heavily used, and some hidden gems.

First, the most used environment of the week is EndlessTerminals by @gandhikanishk with 830k+ tool calls.

https://t.co/ZpustB7zYK

🧵

[Shashwat Goel @ShashwatGoel7]

Cool idea from @AashaySachdeva: unified environment interfaces like @OpenReward can enable LLM meta-learning research!

Pleased with where things are going with more parts of the stack accessible publically. For e.g. I now look forward to weekly @tinkerapi roundups as much as John Oliver episodes!

[aashay sachdeva @AashaySachdeva]

Played around with this. This was exactly something I was looking for!

Tried a few things -
Creating an env - pretty dope! end to end claude was able to port it from github with only minor issues. One shotted @ShashwatGoel7 OpenForecaster env here. A lot more people should contribute their own envs. I hope they launch monetisation here.

Running a curator over env tasks during RL - When there are so many tasks, which one should you focus on? This is the auto-curriculum/meta-learning bit. I am still not able to beat random/pass@k but I think signals are there over long run this will help with diversity. This obviously has a power law, every run will have top envs dominating but I feel those 20% random tasks will give a big boost to any model.

optimise the GEPA optimiser - gepa is great but pretty slow. What if we could teach a model to do this better? This was in my list for so long, finally with openreward was able to attempt it.