llm-planning

ChinaTravel: A Real-World Benchmark for Language Agents in Chinese Travel Planning

[ACL 2025] A curated list of papers and resources based on "PlanGenLLMs: A Modern Survey of LLM Planning Capabilities"

Adaptive Iterative Feedback Prompting for Obstacle-Aware Path Planning via LLMs - LM4Planning - AAAI2025

Awesome-LLM-Planning

Plan-and-Solve agent framework decomposing complex multi-step queries into a directed dependency plan

Plan-and-Solve agent framework decomposing complex multi-step queries into a directed dependency plan

PolicyEval checks whether an LLM's output follows the rules you set

EmbedPlan: a fast transition model for LLM planning, learned on frozen text embeddings. Code for the paper 'Textual Planning with Explicit Latent Transitions' (arXiv 2602.04557).

Benchmark measuring how LLM planners fail at robot tasks, not just how often: trap-labelled instructions with machine-checked ground truth, differential-tested against pyperplan, no human or LLM judging anywhere. Every label proof re-run in CI.

Repo for exploring the (in)effectiveness of chain of thought in planning

Heterogeneous GNN policies for constrained zero-shot morphology transfer in legged locomotion with ROS2/Gazebo deployment, YOLO-based vision, and LLM-guided navigation.

The project is intended to evolve into a study prototype for LLM-based systems (e.g., agents, planners, tool calling)

Provenance-locked benchmark and evaluation pipeline for verifiable LLM planning across five PDDL domains.

Benchmarks a 1.5B reasoning model (DeepSeek-R1) vs. SOTA non-reasoning LLMs for text-to-SQL using a generator-discriminator planning framework. Proposes a novel method to extract soft scores from chain-of-thought outputs for fine-grained candidate ranking.