Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning

ICLR 2026 Conference Submission13329 Authors

Keywords: Embodied AI, Long-horizon task, Long-context reasoning

Abstract:

We introduce $\infty$-THOR, a new framework for long-horizon embodied tasks that advances long-context understanding in embodied AI.
$\infty$-THOR provides:
(1) a generation framework for synthesizing scalable, reproducible, and unlimited long-horizon trajectories;
(2) a novel embodied QA task, Needle(s) in the Embodied Haystack, where multiple scattered clues across extended trajectories test agents’ long-context reasoning ability; and
(3) a long-horizon dataset and benchmark suite featuring complex tasks that span hundreds of environment steps, each paired with ground-truth action sequences.
To enable this capability, we explore architectural adaptations, including interleaved Goal-State-Action modeling, context extension techniques, and Context Parallelism, to equip LLM-based agents for extreme long-context reasoning and interaction.
Experimental results and analyses highlight the challenges posed by our benchmark and provide insights into training strategies and model behaviors under long-horizon conditions.
Our work provides a foundation for the next generation of embodied AI systems capable of robust, long-term reasoning and planning.

Primary Area: datasets and benchmarks

Submission Number: 13329