6 papers
Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents
Siqi Fan, Minghao Li, Xiaoqian Ma +6
Hybrid computer-use agents can act through screenshots or call text tools. We find that having a tool available does not settle which way the effect goes. Under one identical GUI-M…
Hint Tuning: Less Data Makes Better Reasoners
Siqi Fan, Minghao Li, Xiaoqian Ma +6
Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning uniformly regardless of prob…
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
Siqi Fan, Xiusheng Huang, Yiqun Yao +6
Large language models (LLMs) can carry out human-like dialogue, but unlike humans, they are stateless due to the superposition property. However, during multi-turn, multi-agent int…
R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning
Zhizheng Jiang, Kang Zhao, Weikai Xu +5
Large reasoning models (LRMs) aim to solve diverse and complex problems through structured reasoning. Recent advances in group-based policy optimization methods have shown promise…
Position-Aware Depth Decay Decoding (): Boosting Large Language Model Inference Efficiency
Siqi Fan, Xuezhi Fang, Xingrun Xing +3
Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. Unlike traditional model compression, which needs retraining, rece…
The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models
Siqi Fan, Bowen Qin, Peng Han +3
Recent thinking models trained with reinforcement learning and backward-checking CoT often suffer from overthinking: they produce excessively long outputs even on simple problems,…