Statistics for language PDDL

Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples

Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples

ChainReactor is a research project that leverages AI planning to discover exploitation chains for privilege escalation on Unix systems. The project models the problem as a sequence of actions to achie...

Code for NeurIPS 2024 paper "AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning"

Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples

An extensible benchmark for evaluating large language models on planning

Convert a PDDL domain into an OpenAI Gym environment.

ChainReactor is a research project that leverages AI planning to discover exploitation chains for privilege escalation on Unix systems. The project models the problem as a sequence of actions to achie...

Code for NeurIPS 2024 paper "AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning"

Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples

An extensible benchmark for evaluating large language models on planning

A lightweight STRIPS planner written in Python.

Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples

ChainReactor is a research project that leverages AI planning to discover exploitation chains for privilege escalation on Unix systems. The project models the problem as a sequence of actions to achie...

Code for NeurIPS 2024 paper "AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning"

An extensible benchmark for evaluating large language models on planning

Reasoning with Language Model is Planning with World Model

Convert a PDDL domain into an OpenAI Gym environment.

Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples

ChainReactor is a research project that leverages AI planning to discover exploitation chains for privilege escalation on Unix systems. The project models the problem as a sequence of actions to achie...

An extensible benchmark for evaluating large language models on planning

No description

Reasoning with Language Model is Planning with World Model

A lightweight STRIPS planner written in Python.

Convert a PDDL domain into an OpenAI Gym environment.