Technical blogs

• LLM Powered Autonomous Agents from Lillian Weng

Papers

LLM Reasoning

• Chain-of-Thought Reasoning Without Prompting
• Large Language Models Cannot Self-Correct Reasoning Yet
• Premise Order Matters in Reasoning with Large Language Models
• Chain-of-Thought Empowers Transformers to Solve Inherently Serial Problems

LLM agents: brief history

• WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
• ReAct: Synergizing Reasoning and Acting in Language Models

Agentic AI Frameworks & AutoGen

• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
• StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows

Enterprise trends for generative AI, and key components of building successful agents/applications

• Google Cloud expands grounding capabilities on Vertex AI
• The Needle In a Haystack Test: Evaluating the performance of RAG systems
• The AI detective: The Needle in a Haystack test and how Gemini 1.5 Pro solves it

Compound AI Systems & the DSPy Framework

• Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
• Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together

Agents for software Developement

• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents

AI Agents for Enterprise Workflows

• WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
• WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
• TapeAgents: a Holistic Framework for Agent Development and Optimization

Towards a unified framework of Neural and Symbolic Decision Making

• Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
• Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
• Composing Global Optimizers to Reasoning Tasks via Algebraic Objects in Neural Nets
• SurCo: Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems

Project GROOT: A Blueprint for Generalist Robotics

• Voyager: An Open-Ended Embodied Agent with Large Language Models
• Eureka: Human-Level Reward Design via Coding Large Language Models
• DrEureka: Language Model Guided Sim-To-Real Transfer

Open-Source and Science in the Era of Foundation Models

• Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Measuring Agent capabilities and Anthropic’s RSP

• Announcing our updated Responsible Scaling Policy
• Developing a computer use model

Towards Building Safe & Trustworthy AI Agents and A Path for Science‑ and Evidence‑based AI Policy

• A Path for Science‑ and Evidence‑based AI Policy
• DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
• Representation Engineering: A Top-Down Approach to AI Transparency
• Extracting Training Data from Large Language Models
• The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks

Test-time Scaling

• s1: Simple test-time scaling

General Agent (using LLM)

• Open Sourcing $\pi_0$
• OpenVLA: An Open-Source Vision-Language-Action Model
• REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context In New Environments