4 papers
Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification
Xinyan Ma, Xianhao Ou, Weihao Zhang +6
Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing trip…
The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?
Yirong Zeng, Shen You, Yufei Liu +9
Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical yet under-explored phenomenon: tool overuse, the unnecess…
SCoGen: Scenario-Centric Graph-Based Synthesis of Real-World Code Problems
Xifeng Yao, Dongyu Lang, Wu Zhang +8
Significant advancements have been made in the capabilities of code large language models, leading to their rapid adoption and application across a wide range of domains. However,…
SLIM: Subtrajectory-Level Elimination for More Effective Reasoning
Xifeng Yao, Chengyuan Ma, Dongyu Lang +8
In recent months, substantial progress has been made in complex reasoning of Large Language Models, particularly through the application of test-time scaling. Notable examples incl…