News

• 08/2026 🌋: Check out our new work ACTS accepted to EMNLP 2026 Findings, which builds a controller agent that steers chain-of-thought in-flight for efficient and budget-aware reasoning!

• 05/2026 🌋: Our multi-objective alignment paper is accepted to ICML 2026!

• 04/2026 🌋: Check out our new work HiLL, which learns adaptive, transfer-aware hints for RL that improve reasoning in no-hint settings!