9 papers
EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?
Zhiyuan Peng, Xin Yin, Chenhao Ying +5
Existing agent benchmarks primarily test task completion, tool use, or skill utility, but do not isolate whether a runtime can convert evidence from its own runs into reusable skil…
Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
Yanming Mu, Hao Hu, Feiyang Li +7
Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases.…
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
Shiqi Liu, Zeyu He, Guojian Zhan +10
Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regu…
GUITester: Enabling GUI Agents for Exploratory Defect Discovery
Yifei Gao, Jiang Wu, Xiaoyi Chen +5
Exploratory GUI testing is essential for software quality but suffers from high manual costs. While Multi-modal Large Language Model (MLLM) agents excel in navigation, they fail to…
Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
Zinan Tang, Xin Gao, Qizhi Pei +5
Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to impr…
PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling
Yuxuan Yue, Zukang Xu, Zhihang Yuan +3
Large Language Models (LLMs) face significant challenges in edge deployment due to their massive parameter scale. Vector Quantization (VQ), a clustering-based quantization method,…
CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges
Yu Li, Qizhi Pei, Mengyuan Sun +6
Large language models (LLMs) have demonstrated remarkable capabilities, especially the recent advancements in reasoning, such as o1 and o3, pushing the boundaries of AI. Despite th…
A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis
Xin Gao, Qizhi Pei, Zinan Tang +5
While data synthesis and distillation are promising strategies to enhance small language models, current approaches heavily rely on Large Language Models (LLMs), which suffer from…
RLDBF: Enhancing LLMs Via Reinforcement Learning With DataBase FeedBack
Weichen Dai, Zijie Dai, Zhijie Huang +6
While current large language models (LLMs) demonstrate remarkable linguistic capabilities through training on massive unstructured text corpora, they remain inadequate in leveragin…