8 papers
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Deyao Zhu, Xin Zhou, Shengling Qin +44
Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less unders…
MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
Xiaoyu Wen, Zhida He, Han Qi +7
Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on s…
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama +1
We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree and a threshold , a player must answer whether the root node value of $\math…
PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
Huacan Chai, Zijie Cao, Maolin Ran +11
Large language models (LLMs) have achieved impressive success in single-turn function calling, yet real-world applications such as travel planning or multi-stage data analysis typi…
Natural Language Reinforcement Learning
Xidong Feng, Bo Liu, Yan Song +7
Artificial intelligence progresses towards the "Era of Experience," where agents are expected to learn from continuous, grounded interaction. We argue that traditional Reinforcemen…
ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning
Ziyu Wan, Yunxiang Li, Xiaoyu Wen +8
Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, a…