Research Collection

DeepPlanning

A curated archive of 38 papers related to the benchmark for long-horizon agentic planning with verifiable constraints.

Spanning travel planning, shopping agents, web agents, tool use, foundation models, evaluation frameworks, and LLM reasoning — the full landscape of constrained agent planning research.

Browse Papers Read on arXiv

9 Categories

Primary Paper

1

Planning Benchmarks

5

Travel Planning

8

Shopping and Search Agents

3

Web Agent Benchmarks

4

Tool Use and APIs

3

Foundation Models

6

Agent Evaluation Frameworks

7

LLM Reasoning and Verification

1

From the Blog

View all →

Commentary, analysis, and deep dives into the papers in this collection.