HALO trains an orchestrator policy on verifier-approved refinement trajectories across 11 PDDL domains, matching GPT-5-mini success rates at roughly 45x lower orchestration cost and cutting LLM calls by 40-50%.
Coupling large language models with logic program- ming for robust and general reasoning from text
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
A survey that provides a taxonomy of methods for improving planning in LLM-based agents across task decomposition, plan selection, external modules, reflection, and memory.
citing papers explorer
-
Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents
HALO trains an orchestrator policy on verifier-approved refinement trajectories across 11 PDDL domains, matching GPT-5-mini success rates at roughly 45x lower orchestration cost and cutting LLM calls by 40-50%.
-
LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
-
Understanding the planning of LLM agents: A survey
A survey that provides a taxonomy of methods for improving planning in LLM-based agents across task decomposition, plan selection, external modules, reflection, and memory.