论文阅读 ⁴⁴

2026

论文 · a Survey on Evaluation of LLM-Based Agents 07-13

论文 · a Comprehensive Survey of Agents for Computer Use Foundations, Challenges, and Future Directions 07-13

论文 · Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Understanding 07-08

论文 · MrRoPE: Mixed-Radix Rotary Position Embedding 07-08

论文 · LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation 07-08

论文 · LongBench V2: Towards Deeper Understanding and Reasoning on Realistic Long-Context Multitasks 07-08

论文 · LADM: Long-Context Training Data Selection With Attention-Based Dependency Measurement for LLMs 07-08

论文 · How to Train Long-Context Language Models (Effectively) 07-08

论文 · Understand What LLM Needs：Dual Preference Alignment for Retrieval-Augmented Generation 07-06

论文 · MemoRAG：Boosting Long Context Processing With Global Memory-Enhanced Retrieval Augmentation 07-06

论文 · LightRAG：Simple and Fast Retrieval-Augmented Generation 07-06

论文 · Self-RAG：Learning to Retrieve, Generate, and Critique Through Self-Reflection 07-06

论文 · GraphRAG：From Local to Global 07-06

论文 · RAG综述 07-03

论文 · Memory综述 07-03

论文 · Just-in-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates 07-02

论文 · When to Forget: A Memory Governance Primitive 07-01

论文 · Score-Aware Policy-Gradient and Performance Guarantees Using Local Lyapunov Stability 07-01

论文 · Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents 07-01

论文 · MemGPT: Towards LLMs as Operating Systems 07-01

1
2
3