5 papers
Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
Wei Liu, Siya Qi, Yali Du +1
Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are better understood as self-play and often p…
Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
Wei Liu, Peijie Yu, Michele Orini +2
The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelli…
Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades
Edoardo Pona, Milad Kazemi, Mehran Hosseini +4
Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive exper…
CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
Zhenyi Shen, Hanqi Yan, Linhai Zhang +3
Chain-of-Thought (CoT) reasoning enhances Large Language Models (LLMs) by encouraging step-by-step reasoning in natural language. However, leveraging a latent continuous space for…
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
Wei Liu, Siya Qi, Xinyu Wang +3
Recent advances such as DeepSeek R1-Zero highlight the effectiveness of incentive training, a reinforcement learning paradigm that computes rewards solely based on the final answer…