6 papers
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
Haoyu Wang, Yuliang Song, Tao Li +5
Large Language Models (LLMs) struggle to solve complex combinatorial problems through direct reasoning, so recent neuro-symbolic systems increasingly use them to synthesize executa…
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…
Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
Shenao Zhang, Yaqing Wang, Yinxiao Liu +5
Large Language Models (LLMs) trained via Reinforcement Learning (RL) have exhibited strong reasoning capabilities and emergent reflective behaviors, such as rethinking and error co…
GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning
Jiale Fu, Yaqing Wang, Simeng Han +2
In-context learning (ICL) enhances large language models (LLMs) by incorporating demonstration examples, yet its effectiveness heavily depends on the quality of selected examples.…
Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology
Longchao Da, Xiaoou Liu, Jiaxin Dai +3
Understanding the uncertainty in large language model (LLM) explanations is important for evaluating their faithfulness and reasoning consistency, and thus provides insights into t…
SRSA: A Cost-Efficient Strategy-Router Search Agent for Real-world Human-Machine Interactions
Yaqi Wang, Haipei Xu
Recently, as Large Language Models (LLMs) have shown impressive emerging capabilities and gained widespread popularity, research on LLM-based search agents has proliferated. In rea…