We’re excited to highlight SETA, an open-source RL environment for training and evaluating AI agents from the @CamelAIOrg . A valuable resource for researchers and developers exploring agentic reinforcement learning and complex task environments. Check it out and support the CAMEL-AI community! 🚀 🔗 github.com/camel-ai/seta

This Friday on 🐫 CAMEL-AI Live Talk, Ziyi Wang @Ziyi0_0 is sharing Trajectory2Task: a trajectory-first way to train stronger tool-calling agents with synthesized, verifiable data. Instead of writing tasks first and hoping agents can solve them, Trajectory2Task starts with executable tool-use trajectories, then turns their outcomes into realistic user intents. The result: training data that is diverse, grounded, and actually checkable. If you care about LLM agents, tool use, or synthetic data for post-training, don’t miss this one! 🗓️ Sep 4 · 4 PM UK Time / 8 AM PT · Zoom 📝 Register: forms.gle/aqTzxMy9KqauHQj28

Today we're launching Miles v0.1, an open-source RL framework for LLMs and multimodal models. RL training is easy to start and hard to debug. Miles helps you ensure your run is correct, use hardware efficiently, and keep RL running at scale. Over the past 9 months, 72 contributors have landed 1,326 commits, 85 GPU E2E CI tests, battle-testing Miles on frontier open models like Kimi K3, DeepSeek V4, Qwen 3.8, GLM 5.2, Inkling, MiniMax H3, etc. Miles powers frontier-model development and production RL workloads at @humansand, @periodiclabs, @modal, @DecagonAI, @Eigent_AI, @nebiusai, @IBM and more, on both @NVIDIAAI and @AIatAMD hardware. Here is what we built, and why teams picked Miles🧵

This Friday on 🐫 CAMEL-AI Live Talk, Nishant is unveiling BenchMarker, and it might change how much you trust your favorite benchmarks. He is an NLP PhD candidate at the University of Maryland who cares about making LLM evaluation actually mean something. The idea is simple but sharp: grade benchmarks the way teachers grade exam questions. BenchMarker uses LLM judges to catch three sneaky flaws in multiple choice tests, internet contamination, shortcuts models quietly exploit, and writing errors scored against a 19 rule rubric. Validated against human annotations and run across 12 popular benchmarks, the flaws showed up everywhere. If your work touches evaluation, LLM testing, or agent diagnosis, this one is for you. 🗓 Jul 31 · 1 PM UK (BST) / 8 AM US East (EDT) · Zoom 📝 Register: docs.google.com/forms/d/e/1F…