AI Paper Atlas

Research map / Large language models / Agents, code and math

LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward

Yi Zhao, Siqi Wang, Jing Li

AAAI 2026 · Large language models › Agents, code and math · approach: LLM-driven embodied and driving agents · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LLM-as-Follower reward to format+METEOR GRPO rewards (ablation)SFT+GRPO Qwen2.5-VL-3B · NIG4VI intra-town (no pre-calc)BLEU: 10.912 -> 10.921Improved
add LLM-as-Follower reward to format+METEOR GRPO rewards (ablation)SFT+GRPO Qwen2.5-VL-3B · NIG4VI inter-town (no pre-calc)BLEU: 10.076 -> 10.157Improved
add LLM-as-Follower reward to format+METEOR GRPO rewards (ablation)SFT+GRPO Qwen2.5-VL-3B · NIG4VI intra-townSPICE: 0.279 -> 0.274 (no pre-calc); 0.284 -> 0.286 (with pre-calc)Mixed
add METEOR text reward on top of format reward (ablation)SFT+GRPO Qwen2.5-VL-3B · NIG4VI intra-town (no pre-calc)BLEU: 10.251 -> 10.912Improved
apply LaF-GRPO after SFTQwen2.5-VL-7B · NIG4VI intra-town (no pre-calc)METEOR: 0.518 -> 0.545Improved
apply LaF-GRPO after SFTQwen2.5-VL-7B · NIG4VI inter-town (no pre-calc)BLEU: 9.709 -> 9.002Hurt
apply LaF-GRPO after SFTQwen2.5-VL-3B · NIG4VI intra-town (no pre-calc)BLEU: 9.099 -> 10.921Improved
apply LaF-GRPO directly without SFTQwen2.5-VL-7B · NIG4VI intra-town (no pre-calc)METEOR: 0.211 -> 0.256Improved
increase training samples from 1k to 3k (ablation)SFT+(LaF-GRPO) Qwen2.5-VL-7B · NIG4VI intra-town (no pre-calc)METEOR: 0.529 -> 0.545Improved
increase training samples from 2k to 3k (ablation)SFT+(LaF-GRPO) Qwen2.5-VL-7B · NIG4VI intra-town (with pre-calc)METEOR: 0.550 -> 0.556No clear effect
use LaF reward instead of standard GRPO (LLM judge) (ablation)Qwen2.5-VL · NIG4VI inter-townnavigational accuracy (%): 67.3% -> 68.1%No clear effect
use LaF reward instead of standard GRPO (human study) (ablation)Qwen2.5-VL · NIG4VI inter-townpreference rate: 24% -> 76%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy