材料总目录 按主题大类归类 · 全部 50 篇

"Agentic Design Patterns Part 1: Four AI Agent Strategies That Improve GPT-4 and GPT-3.5 Performance"

"Towards Execution-Grounded Automated AI Research"

"The Shift from Models to Compound AI Systems"

"Effective Context Engineering for AI Agents"

"Building Effective Agents"

"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT"

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

"Model Context Protocol Specification (Version 2025-06-18)"

"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines"

"ReAct: Synergizing Reasoning and Acting in Language Models"

"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory"

"Agent Memory: How to Build Agents That Learn and Remember"

"MemGPT: Towards LLMs as Operating Systems"

"Generative Agents: Interactive Simulacra of Human Behavior"

"Why Do Multi-Agent LLM Systems Fail?"

"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration"

Don't Sleep on Single-agent Systems

"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation"

"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning"

Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs

"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters"

"Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together"

Data Flywheels for LLM Applications

"Large Language Models for Data Annotation and Synthesis: A Survey"

"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences"

"SWE-smith: Scaling Data for Software Engineering Agents"

"LIMA: Less Is More for Alignment"

"tinyBenchmarks: evaluating LLMs with fewer examples"

"How to Build Good Language Modeling Benchmarks"

"Establishing Best Practices for Building Rigorous Agentic Benchmarks"

"Demystifying evals for AI agents"

"AutoMetrics: Approximate Human Judgments with Automatically Generated Evaluators"

"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena"

"AutoLibra: Agent Metric Induction from Open-Ended Human Feedback"

"Introducing Anthropic's Responsible Scaling Policy"

"Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset"

"Understanding prompt injections: a frontier security challenge"

"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action"

"Contextualized Privacy Defense for LLM Agents"

"Searching for Privacy Risks in LLM Agents via Simulation"

Best practices for Claude Code

"SWE-bench: Can Language Models Resolve Real-World Github Issues?"

"OpenHands: An Open Platform for AI Software Developers as Generalist Agents"

"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering"

"Effective harnesses for long-running agents"

"Creating General User Models from Computer Use"

"Learning Next Action Predictors from Human-Computer Interaction"

"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments"

"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents"