Generate-then-Rank: Learning Symbolic Goal Interpretation for Embodied Agents

The proposed method outperformed the baseline models including LLMs with simple prompting, chain-of-thought, and knowledge graph based approaches. It comes from a paper posted to arXiv on 6 November 2026. Goal interpretation is to translate a natural language instruction into a formal symbolic goal that a planner can execute. It is critical for embodied agents because any error here propagates to every downstream planning and action step. Doing it well requires both generating suitable candidates and reliably selecting among them. We present a two-stage generate-then-rank approach to Goal Interpretation in the Embodied Agent Interface (EAI). First, supervised fine-tuning adapts a Large Language Model (LLM) to EAI's output convention. Second, Candidate-Output Ranking from Errors (CORE) learns preferences over complete outputs from the model's own generated alternatives. We conducted experiments on the household scenes of the Embodied Agent Interface Benchmark. Multiple open source LLMs including DeepSeek-V3 chat, DeepSeek-Reasoner, and Qwen2.5-7B and Qwen2.5-72B were evaluated.

Why it counts

The proposed method outperformed the baseline models including LLMs with simple prompting, chain-of-thought, and knowledge graph based approaches. First, supervised fine-tuning adapts a Large Language Model (LLM) to EAI's output convention.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.