AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
How Code Empowers LLMs
A survey on why training LLMs with code data produces capabilities well beyond coding itself.
CogAgent
Tsinghua's CogAgent is an 18B-parameter visual-language model purpose-built for GUI understanding and navigation, with unusually high input resolution.
From Gemini to Q-Star
A 300+-paper survey mapping the state of Generative AI and the research frontiers that followed the Gemini + rumored Q* news cycle.
Survey of Reasoning with Foundation Models
A comprehensive survey of reasoning with foundation models, covering tasks, methods, benchmarks, and future directions.
AppAgent
Introduces an LLM-based multimodal agent that operates real smartphone apps through touch actions and screenshots.
ReST Meets ReAct
Proposes a ReAct-style agent that improves itself via reinforced self-training on its own reasoning traces.
RAG for LLMs
A broad survey of Retrieval-Augmented Generation research, organizing the rapidly growing literature into a coherent map.
Pearl
Meta's Pearl is a production-ready reinforcement learning agent package designed for real-world deployment constraints.
GNoME
DeepMind's Graph Networks for Materials Exploration (GNoME) is an AI system that discovered 2.2 million new crystal structures, including 380,000 thermodynamically stable ones.
Hitchhiker's Guide From CoT to Agents
A survey mapping the conceptual evolution from chain-of-thought reasoning to modern language-agent frameworks.
GAIA
Meta's GAIA is a benchmark for general AI assistants that requires reasoning, multimodal handling, web browsing, and tool use to solve real-world questions.
MedAgents
A collaborative multi-round framework for medical reasoning that uses role-playing LLM agents to improve accuracy and reasoning depth.
JARVIS-1
An open-world multimodal agent for Minecraft that combines perception, planning, and memory into a self-improving system.
LLMs Can Deceive Users (Trading Agent)
Apollo Research shows that a helpful, honest LLM stock-trading agent can spontaneously deceive users under pressure.
On the Road with GPT-4V
An exhaustive evaluation of GPT-4V applied to autonomous driving scenarios.
Managing AI Risks (Bengio, Hinton, et al.)
A high-profile position paper by leading AI researchers laying out risks from upcoming advanced AI systems.
Branch-Solve-Merge (BSM)
BSM decomposes LLM tasks into parallel sub-tasks via three LLM-programmed modules: branch, solve, and merge.
LLMs for Software Engineering
A comprehensive survey of LLMs for software engineering covering models, tasks, evaluation, and open challenges.
OpenAgents
An open platform for running and hosting real-world language agents, including three distinct agent types.
AutoMix
AutoMix routes queries between LLMs of different sizes based on smaller-model confidence, saving cost without sacrificing quality.
Video Language Planning
Enables synthesizing complex long-horizon video plans for robotics via tree search over vision-language and text-to-video models.
UniSim (Universal Simulator)
Google's UniSim learns a universal generative simulator of real-world interactions from diverse video + action data.
MemWalker
MemWalker treats the LLM as an interactive agent that traverses a tree-structured summary of long text.
FireAct (Language Agent Fine-tuning)
Explores fine-tuning LLMs specifically for language-agent use, demonstrating consistent gains over prompting alone.