Ching-An Cheng @ICML2025

#Trace and #GenerativeOptimization enables training a new kind of agents and model architectures. Come to chat with us and learn how #Trace works behind the scene and its theory. We will present its poster at #NeurIPS2024 on Friday (4:30pm-7:30pm, E Exhibit Hall A-C #2709).…

🔄 We were nominated for Oral+top 1 in the MATH-AI workshp at #ICML! 🚨Why? ≈46 % of GitHub commits are AI-generated—but can we verify them correct? 📢 VeriBench challenges agents; turn Python into Lean code! 🧵1/14 📃 Paper: openreview.net/forum?id=rWkGF…

We are organizing a workshop tomorrow at #icml25. Come join us and checkout the latest on programmatic representation and agent learning

Our #ICML2025 Programmatic Representations for Agent Learning workshop will take place tomorrow, July 18th, at the West Meeting Room 301-305, exploring how programmatic representations can make agent learning more interpretable, generalizable, efficient, and safe! Come join us!

Starting my #ICML2025. Will be here until Saturday. Looking forward to meeting everyone 😀

Provably Learning from Language Feedback TLDR: RL theory can help us do better inference-time exploration with feedback. Work done with @wanqiao_xu, @ruijie_zheng12, @chinganc_rl, @adityamodi94, @adith387 📰 arxiv.org/pdf/2506.10341 📍EXAIT Best Paper/Oral Sat 8:45-9:30 am

Super excited about this work done by our former intern @wanqiao_xu . We show Learning from Language Feedback (LLF) with LLM can be formally studied with provable no-regret learning algorithms. This result builds a foundation toward new theories for LLM learning and optimization.

Decision-making with LLM can be studied with RL! Can an agent solve a task with text feedback (OS terminal, compiler, a person) efficiently? How can we understand the difficulty? We propose a new notion of learning complexity to study learning with language feedback only. 🧵👇

Check out this new optimization framework (github.com/datarobot/syftr) by #DataRobot that can automatically search for "Pareto-optimal" solutions for agentic workflows. It's built on our LLM generative optimization framework #Trace. Excited to see more applications of #Trace! 😎

Our ICML & RLC workshops welcome contributions using programmatic representations as policies, reward functions, skill libraries, task generators, environment models, etc., to improve interpretability, generalization, efficiency, & safety in agent learning & RL! Please retweet 🙏

Started my new job at #Google Research recently. Super excited about what can be done here. 😎

The RLC accepted workshops list is out (link in next tweet)! Programmatic RL Causal RL RL and videogames Inductive biases and RL and returning from last year: RL beyond rewards, finding the frame, and RL in practice!

Announcing AutoGen 0.4, fully reimagined library for building advanced agentic AI systems, developed to improve code quality and robustness. Its asynchronous, event-driven architecture is designed to support dynamic, scalable workflows. Learn more: msft.it/6012ohgli

MSR is hiring robotics researchers!! Good time to join! 😎

I'm hiring researchers for my physically embodied AI & robotics team at MSR! 🤖👇 jobs.careers.microsoft.com/us/en/job/1778… Physically embodied agents, both in the humanoid robot form and beyond, are the new computational platform of tomorrow. As with personal computers many decades ago, these…

#NeurIPS2024 Super fun talking to tons of people yesterday. Like seeing people got genuinely surprised and laughed. Non stop 3 hrs talking. Finally the poster session is over and I can take a break :). Looking forward to seeing new research inspired by #Trace. Great job…