7 papers
Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
Peter Chen, Xi Chen
We study fixed-confidence best-action identification (BAI) in stochastic minimax trees. This problem is increasingly relevant in modern AI planning, where deep minimax search and M…
Reward-free Alignment for Conflicting Objectives
Peter Chen, Xiaopeng Li, Xi Chen +1
Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflictin…
Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
Peter Chen, Xiaopeng Li, Ziniu Li +2
Reinforcement learning (RL) has proven effective in strengthening the reasoning capabilities of large language models (LLMs). A widely adopted method, Group Relative Policy Optimiz…
Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
Peter Chen, Xiaopeng Li, Ziniu Li +3
This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Model…
GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
Jiacheng Guo, Ling Yang, Peter Chen +6
Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenE…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…