aiqbench analysis
This paper proposes HiMeco, a self-evolving agent for embodied spatial tasks that diagnoses failures across perception, exploration, and planning, then stores reusable strategies and parameterized skills in memory between rounds while keeping model weights frozen. The key contribution is separating which component caused a failure, which pure execution feedback struggles to do. Results are reported on ESI-Bench and EmbSpatial-Bench, but the benchmark-based evidence is still narrow, so readers should check how well the gains hold up in real environments and against stronger baselines.
Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence
arXiv:2610.20312v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have made substantial progress in spatial reasoning, and self-evolving agents further extend these capabilities to embodied environments by learning from interactions. However, current self-evolution remains particularly challenging in embodied spatial tasks, complex and multi-step decisions from partial visual evidence making it difficult to determine why an execution fails. The failure may stem from misperception, insufficient exploration, or incorrect planning, yet execution feedback alone rarely reveals which component is responsible. As a result, simply accumulating interaction experience can reinforce ineffective strategies. To address this, we propose HiMeco, a brain-inspired self-evolving agent for embodied spatial intelligence, inspired by metacognitive monitoring and hippocampal memory consolidation. Through Hippocampal-Metacognitive Reflection, HiMeco diagnoses failures in perception-exploration-planning (PEP), then compares execution attempts to derive reusable strategies and guidance for avoiding recurring errors. It also abstracts interaction programs into parameterized skills, using evidence contracts and execution-based validation to determine their retention and reuse. These strategies and skills guide subsequent interactions, with memory updated only between rounds and model parameters kept frozen. HiMeco achieves state-of-the-art performance on ESI-Bench, and it also improves accuracy on EmbSpatial-Bench by 3.94 percentage points without evolution.
Abstract:Vision-Language Models (VLMs) have made substantial progress in spatial reasoning, and self-evolving agents further extend these capabilities to embodied environments by learning from interactions. However, current self-evolution remains particularly challenging in embodied spatial tasks, complex and multi-step decisions from partial visual evidence making it difficult to determine why an execution fails. The failure may stem from misperception, insufficient exploration, or incorrect planning, yet execution feedback alone rarely reveals which component is responsible. As a result, simply accumulating interaction experience can reinforce ineffective strategies. To address this, we propose HiMeco, a brain-inspired self-evolving agent for embodied spatial intelligence, inspired by metacognitive monitoring and hippocampal memory consolidation. Through Hippocampal-Metacognitive Reflection, HiMeco diagnoses failures in perception-exploration-planning (PEP), then compares execution attempts to derive reusable strategies and guidance for avoiding recurring errors. It also abstracts interaction programs into parameterized skills, using evidence contracts and execution-based validation to determine their retention and reuse. These strategies and skills guide subsequent interactions, with memory updated only between rounds and model parameters kept frozen. HiMeco achieves state-of-the-art performance on ESI-Bench, and it also improves accuracy on EmbSpatial-Bench by 3.94 percentage points without evolution.
Artificial Intelligence (cs.AI)
arXiv:2610.20312 [cs.AI]
(or arXiv:2610.20312v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.20312 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 279 words
Related coverage
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · Jun 12, 2026
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · Aug 3, 2026
An Organizational Second Brain: Building an AI That Learns From Experts
Meta Engineering · Sep 2, 2026