AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
The Dawn of LMMs (GPT-4V Deep Dive)
Microsoft's exhaustive 166-page analysis of GPT-4V's capabilities and limitations.
Self-Taught Optimizer (STOP)
Proposes recursively self-improving code generation where an LLM-scaffolded program improves itself.
Qwen
Alibaba releases the Qwen family of open LLMs with strong tool-use and planning capabilities for language agents.
Compositional Foundation Models (HiP)
Proposes foundation models that compose multiple expert foundation models trained on different modalities to solve long-horizon goals.
OWL (LLMs for IT Operations)
Proposes OWL, an LLM specialized for IT operations through self-instruct fine-tuning on IT-specific tasks.
The Rise and Potential of LLM-Based Agents
A comprehensive survey of LLM-based agents covering construction, capability, and societal implications.
Agents Library
An open-source library for building autonomous language agents with first-class support for planning, memory, tools, and multi-agent communication.
ChatDev (Communicative Agents for Software Development)
ChatDev is a virtual chat-powered software company where LLM agents take on roles in a waterfall-model dev process.
GPT Solves Math Problems Without a Calculator
Demonstrates that with sufficient training data, even a small language model can perform accurate multi-digit arithmetic.
OPRO (LLMs as Optimizers)
DeepMind's OPRO uses LLMs as general-purpose optimizers over natural-language-described problems.
Cognitive Architectures for Language Agents (CoALA)
Princeton proposes CoALA, a systematic framework for understanding and building language agents.
Q-Transformer
Google's Q-Transformer is a scalable RL method for training multi-task robotic policies from large offline datasets.
LLM-Based Autonomous Agents Survey
A comprehensive survey of LLM-based autonomous agents covering construction and applications.
Prompt2Model
CMU's Prompt2Model automates the path from a natural-language task description to a deployable small special-purpose model.
Outlines (Efficient Guided Generation)
A library for guided LLM text generation that enforces structural constraints with minimal overhead.
D-Bot (LLMs as Database Administrators)
Introduces D-Bot, an LLM-based framework that continuously acquires database-administration knowledge from textual sources.
AgentBench
Tsinghua's AgentBench is a multidimensional benchmark for LLM-as-Agent reasoning and decision-making across 8 environments.
LLMs for HVAC Control
Microsoft applies LLMs to industrial control tasks (HVAC for buildings), comparing against RL baselines.
ToolLLM
Tsinghua's ToolLLM enables LLMs to interact with 16,000+ real-world APIs through a comprehensive framework for tool-using LLMs.
MetaGPT
MetaGPT is a multi-agent framework that encodes standardized operating procedures (SOPs) for complex problem solving.
Dynalang (Agents Model the World with Language)
UC Berkeley's Dynalang agent learns a multimodal world model predicting future text, video, and rewards.
WavJourney
Leverages LLMs to orchestrate audio generation models for compositional storytelling.
Generative TV & Showrunner Agents
Fable Studio's approach to generate episodic TV content using LLMs and multi-agent simulation.
A Survey on Evaluation of LLMs
A comprehensive overview of evaluation methods covering what, where, and how to evaluate LLMs.