Related papers: Learning from Trials and Errors: Reflective Test-T…

This study examines the development of reflective practice among students on a four-year work-based Software Engineering program. Using two established models of reflection - Boud et al.'s Model of Reflective Process and Bain et al.'s 5R…

Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a…

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reasoning, a prerequisite for solving complex real-world…

Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene…

In the aftermath of COVID-19, many universities implemented supplementary "reinforcement" roles to support students in demanding courses. Although the name for such roles may differ between institutions, the underlying idea of providing…

The integration of Large Language Models (LLMs) into robotics has unlocked unprecedented capabilities in high-level task planning. However, most current systems operate in an open-loop fashion, where LLMs act as one-shot planners, rendering…

Large Language Models (LLMs) have opened transformative possibilities for human-robot collaboration. However, enabling real-time collaboration requires both low latency and robust reasoning, and most LLMs suffer from high latency. To…

In this article, we introduce 'Internalized Self-Correction' (InSeC) for large language models (LLMs). While many approaches exist for self-reflection at inference time, we propose a novel method that combines ideas from negative sampling,…

We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as…

In the endeavor to make autonomous robots take actions, task planning is a major challenge that requires translating high-level task descriptions to long-horizon action sequences. Despite recent advances in language model agents, they…

While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources. In addition to the…

Recent advances in prompt optimization, exemplified by methods such as TextGrad, enable automatic, gradient-like refinement of textual prompts to enhance the performance of large language models (LLMs) on specific downstream tasks. However,…

Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as science, coding, and mathematics. However, the effectiveness of…

The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future…

Self-reflection for Large Language Models (LLMs) has gained significant attention. Existing approaches involve models iterating and improving their previous responses based on LLMs' internal reflection ability or external feedback. However,…

The advancement of embodied intelligence is accelerating the integration of robots into daily life as human assistants. This evolution requires robots to not only interpret high-level instructions and plan tasks but also perceive and adapt…

Vision-Language-Action Models (VLAs) inherit their visual and linguistic capabilities from Vision-Language Models (VLMs), yet most VLAs are built from off-the-shelf VLMs that are not adapted to the embodied domain, limiting their downstream…

Embodied agents performing complex tasks are susceptible to execution failures, motivating the need for effective failure recovery mechanisms. In this work, we introduce a conditional multistage failure recovery framework that employs…

In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifically, we identify temporal consistency in the absence of…