Strong LLM optimizers act as local refiners with incremental improvements and semantic localization, while weaker ones show large drift and stagnation; solution novelty predicts success only when searches stay localized around high-performing regions.
Trajevo: Designing trajectory prediction heuristics via llm-driven evolution
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A review categorizing 2020-2025 deep learning methods for multi-agent human trajectory prediction by architecture, input representations, and strategies, with emphasis on ETH/UCY benchmark evaluations and future challenges.
citing papers explorer
-
What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
Strong LLM optimizers act as local refiners with incremental improvements and semantic localization, while weaker ones show large drift and stagnation; solution novelty predicts success only when searches stay localized around high-performing regions.
-
Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review
A review categorizing 2020-2025 deep learning methods for multi-agent human trajectory prediction by architecture, input representations, and strategies, with emphasis on ETH/UCY benchmark evaluations and future challenges.