10 papers
AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers
Tianyu Huai, Tingshuo Fan, Xinchi Chen +5
As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important. Existing benchmark…
Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
Qianjun Pan, Yutao Yang, Junsong Li +5
Retrieval-augmented generation (RAG) enables agents to access external knowledge at inference time, but it primarily retrieves fragmented declarative evidence, leaving agents to re…
FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow
Bihao Zhan, Zongsheng Cao, Jie Zhou +2
Graph-based retrieval-augmented generation (GraphRAG) is effective for knowledge-intensive and multi-hop query tasks; however, many existing methods primarily seed entity-based gra…
MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis
Lushi Pu, Weiming Zhang, Xinheng Xie +6
Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty. Mo…
Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Bihao Zhan, Jie Zhou, Junsong Li +9
Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. T…
LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
Junsong Li, Jie Zhou, Bihao Zhan +7
Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic…