Subject
8 entries
Planning
Bookmarks
Thymer: Smart Editor for Thoughts and Planning
Thymer is a browser-based planning and note-taking tool that combines outlining, task management, and structured planning in one editor — developer-style features (command palette, split panels, keyboard shortcuts) with end-to-end encryption and self-hosting options. Positioned as an IDE for thoughts rather than a shopping-list task manager.
TravelPlanner: A Benchmark for Real-World Planning with Language Agents
TravelPlanner is a benchmark for evaluating LLM planning capabilities in complex real-world scenarios — GPT-4 scored 0.6% on the full benchmark, revealing that even the best LLMs struggle with multi-constraint sequential planning. A sobering check on agentic AI ambitions.
Avenging Polanyi's Revenge: LLM Approximate Omniscience in Planning
A talk titled 'Avenging Polanyi's Revenge' arguing that LLMs' approximate omniscience changes planning — they've absorbed tacit knowledge that previously required human experts, enabling a different category of automated planning than rule-based systems allowed.
llm-reasoners: Advanced LLM Reasoning Algorithms
llm-reasoners is a library for advanced LLM reasoning algorithms — implementing Tree of Thoughts, RAP (Reasoning via Planning), and other structured reasoning approaches over standard chain-of-thought. Useful for research into how to get LLMs to reason more reliably on complex tasks.
LLM Powered Autonomous Agents
Lilian Weng's survey post on LLM-powered autonomous agents — covering the planning, memory, and tool use components that compose into agent architectures. One of the most cited and comprehensive overviews of the agent design space from mid-2023.
Algorithms for Decision Making (2-column edition)
A two-column or second-edition variant of the MIT Press textbook by Mykel Kochenderfer covering decision-making under uncertainty, from MDPs and POMDPs through reinforcement learning and multi-agent systems. This copy predates the primary 2023-01 vault entry and may represent an earlier draft or reformatted version.
A Practical Guide to Multi-Objective Reinforcement Learning and Planning
A Springer survey on multi-objective reinforcement learning and planning — covers scalarization, Pareto-based methods, and utility-based approaches for agents that must balance competing rewards. Useful reference for RL research where single-reward framing is inadequate.
Excellent Street Views: SF Planning Design Principles
SF Planning Department's 'Excellent Street Views' document — a guide to the design principles that make streets walkable and visually engaging. Covers building setbacks, facade continuity, street-level activation, and the visual corridor principles that distinguish human-scale streets from car-oriented ones.