💥Time-R1 is here! Can a 3B LLM truly grasp time? 🤔 YES! Excited to share our new work, Time-R1: Towards Comprehensive Temporal Reasoning in LLMs 🚀 Check it out: 📖 Paper: arxiv.org/abs/2505.13508 💻 Code: github.com/ulab-uiuc/Time… #TemporalReasoning #RL #LLMs

📢 New Paper Drop: From Solving to Modeling! LLMs can solve math problems — but can they model the real world? 🌍 📄 arXiv: arxiv.org/pdf/2505.15068 💻 Code: github.com/qiancheng0/Mod… Introducing ModelingAgent, a breakthrough system for real-world mathematical modeling with LLMs.

⚠️ Rogue AI scientists? 🛡️ SafeScientist rejects unsafe prompts for ethical discoveries. Check out paper ➡️ (arxiv.org/pdf/2505.23559) #AISafety #LLM #SafeAI #AI

Can LLMs make rational decisions like human experts? 📖Introducing DecisionFlow: Advancing Large Language Model as Principled Decision Maker We introduce a novel framework that constructs a semantically grounded decision space to evaluate trade-offs in hard decision-making

Super excited to begin my Applied Scientist Internship at Amazon, which is my first internship in the industry. I'm looking forward to conducting interesting and insightful research on the efficient reasoning of LLMs!

How can we unlock generalized reasoning? ⚡️Introducing Energy-Based Transformers (EBTs), an approach that out-scales (feed-forward) transformers and unlocks generalized reasoning/thinking on any modality/problem without rewards. TLDR: - EBTs are the first model to outscale the

We're pleased to announce that SafeSwitch has been accepted to EMNLP 2025! Many thanks to the collaborators for their help with this amazing project! Cheng Qian Xiusi Chen Yuji Zhang Denghui Zhang Heng Ji Paper: arxiv.org/pdf/2502.01042

Interpretability: Understanding how AI models think youtu.be/fGKNUvivvnc?si… via YouTube Anthropic Anthropic’s new video dives into AI interpretability—how models think & why it matters 🧠✨ Our EMNLP paper SafeSwitch takes a similar path: leveraging internal activations

🚨 New from UIUC x Stanford x AMD: AgentDebug: Where LLM Agents Fail and How They Can Learn From Failures 🔍🤖 LLM agents fail due to early errors that snowball—yet lack tools to trace & fix them. ✅ AgentDebug Debugger 📄 arxiv.org/abs/2509.25370 🛠️ github.com/ulab-uiuc/Agen…

Introducing Multi-Agent Evolve 🧠 A new paradigm beyond RLHF and RLVR: More compute → closer to AGI No need for expensive data or handcrafted rewards We show that an LLM can self-evolve — improving itself through co-evolution among roles (Proposer, Solver, Judge) via RL — all