Beihang University · 13 records

dateidtitleauthorsvenue↑
2026-10-31W7213594818Voltage–Current-Emission Framework of Time-Resolved ElectroluminescenceHui Bao et al.Nano Letters
2026-10-202610.21791RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-AgentHuan Zhang et al.arXiv7
2026-09-292609.33391Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon AgentsMingju Chen et al.arXiv4
2026-09-292609.32754Adaptive Consistency Graph for Long-Horizon AgentsJiecong Wang et al.arXiv3
2026-09-222609.06052SkillSpec: Intent-Masked Specification Reasoning for Agent Skill CorrectnessYizhuo Zhang et al.arXiv11
2026-09-112609.11156UniH^3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image RestorationZhiwen Yang et al.arXiv3
2026-08-112608.09420Intent Speaks Louder: Controllable User Simulation Beyond Response ImitationBo Wang et al.arXiv5
2026-07-242607.19238FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial DocumentsXianfu Cheng et al.arXiv7
2026-07-012607.01213RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility RescueZhihao Lin et al.arXiv3
2026-06-292606.26979How Much Static Structure Do Code Agents Need? A Study of Deterministic AnchoringZhihao Lin et al.arXiv2
2026-06-292606.26978To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program RepairZhihao Lin et al.arXiv1
2026-05-292605.29507Xetrieval: Mechanistically Explaining Dense RetrievalZhixin Cai et al.arXiv2
2026-05-142605.05704SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent SafetyZhe Liu et al.arXiv1