Research

2026 · TMLR The Landscape of Agentic Reinforcement Learning for LLMs: A Survey 2025 · TMLR HoSNNs: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds 2025 · EMNLP ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks 2025 · arXiv ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks 2025 · arXiv Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives 2025 · arXiv The Landscape of Agentic Reinforcement Learning for LLMs: A Survey 2025 · arXiv Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts 2025 · arXiv Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE 2025 · arXiv Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning 2025 · arXiv LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge 2024 · arXiv DS2TA: Denoising Spiking Transformer with Attenuated Spatiotemporal Attention 2024 · Frontiers in Neuroscience Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization 2023 · arXiv HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds 2023 · arXiv UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities 2023 · arXiv DISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention