From the source

[NeurIPS 2023] Large Language Model-Based Autonomous Agents

Research paper

Image published with the post by LG AI Research — Image from lgresearch.ai

Summary by forck

LLM-based autonomous agent research presented at NeurIPS 2023, covering general-purpose agents (Tree of Thoughts, Reflexion, AdaPlanner, SwiftSage) and domain-specific agents including web agents (Mind2Web), coding agents (InterCode), and embodied agents (DEPS).

From the source
This post will introduce LLM-based autonomous agent research introduced at NeurIPS 2023, divided into (1) general-purpose LLM agent research, (2) domain-specific LLM agent research, and (3) ongoing AI agent research at AI Research.
lgresearch.ai

Most covered

Meta Introducing Muse Spark Open, The Most Capable US Open‑Weight Model to Date
TestingCatalog: “ICYMI: Meta's Muse Spark Open is optimized for new Mac Studio”
Reporting · 48 outlets
Meta· 15 Oct
Introducing Muse Spark Open, The Most Capable US Open‑Weight Model to Date
Anthropic Investing in the public benefit
The Guardian: “AI firm Anthropic to commit 5% of shares to fund for ‘public good’”
Reporting · 29 outlets
Image from anthropic.com
Anthropic· 18 Oct
Investing in the public benefit
Anthropic An update on independent evaluators
The Decoder: “Anthropic gives METR inside access to audit its AI models and safety practices”
Reporting · 11 outlets
Image from anthropic.com
Anthropic· 15 Oct
An update on independent evaluators
Meta Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster
Unite.AI: “Meta Details Prometheus Supercluster Scaling Toward 1 Million GPUs”
Reporting · 5 outlets
Image from engineering.fb.com
Meta· 19 Oct
Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster
MiniMax MiniMax M3.1 Flash: Redefining Agent Performance and Cost
The Decoder: “MiniMax M3.1 Flash shows China's AI price race has no floor in sight”
Reporting · 4 outlets
Image from minimax.io
MiniMax· 19 Oct
MiniMax M3.1 Flash: Redefining Agent Performance and Cost

Other stories

Other stories

Other stories

[NeurIPS 2023] Large Language Model-Based Autonomous Agents

Summary by forck

From the source

Other stories

[ICML2026] Solving the Problem of Data Scarcity Using Riemannian Geometry

[ICML2026] Application of Mechanistic Interpretability: Understanding Graph Transformers (TokenGT)

[ICML2026] MCFlow, a New Integrated Model for AI-Generated Inorganic Materials

LG Aimers 9th: Forecasting Pitch Control with AI

LG AI Talk Concert 2026 Day 2: EXAONE based Products and Vision

LG AI Talk Concert 2026: ‘Expert AI’ Solving Complex Industrial Challenges