From the 1 of 37 linked papers with an AI index.
37 papers
Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations
Weijie Liang, Yuanfeng Song, Xing Chen +3
Visual modality has recently been explored as a way to compress textual tokens, including rendering code as images for static code understanding. We study whether this representati…
SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
Mingxuan Zheng, Yujin Zhou, Chuxue Cao +6
LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills. These skills are lightweight, reusable textual artifacts that are loaded into the a…
Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
Hao Wang, Hao Gu, Hongming Piao +6
The paper introduces CurioSFT, an entropy-preserving supervised fine-tuning approach that uses adaptive self-distillation to keep exploration abilities in large reasoning models, l…
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
Chuxue Cao, Jinluan Yang, Haoran Li +8
Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic system…
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
Chuxue Cao, Mengze Li, Juntao Dai +7
Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas. However, their effectiveness in complex mathema…
InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents
Zhenghao Zhu, Yuanfeng Song, Xin Chen +5
Data analysis has become an indispensable part of scientific research. To discover the latent knowledge and insights hidden within massive datasets, we need to perform deep explora…