6 accepted papers
Robotic planning tasks often involve diverse complexities, which make adaptive improvement through reflection particularly challenging. Existing LLM-based approaches typically rely on fixed routines, lacking the ability to adjust to task-specific complexity and often leading to redundant reflections…
Autonomous error correction is critical for domestic robots to achieve reliable execution of complex long-horizon tasks. Prior work has explored self-reflection in Large Language Models (LLMs) for task planning error correction; however, existing methods are constrained by inflexible self-reflection
Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways. At the same time, thanks to improvements in large language models (LLMs), there has also been a rapid development in AI agents that…
We interact with computers on an everyday basis, be it in everyday life or work, and many aspects of work can be done entirely with access to a computer and the Internet. At the same time, thanks to improvements in large language models (LLMs), there has also been a rapid development in AI agents th…
Recent planning methods based on Large Language Models typically employ the In-Context Learning paradigm. Complex long-horizon planning tasks require more context(including instructions and demonstrations) to guarantee that the generated plan can be executed correctly. However, in such conditions, L…
There has been significant progress in developing reinforcement learning (RL) training systems. Past works such as IMPALA, Apex, Seed RL, Sample Factory, and others, aim to improve the system's overall throughput. In this paper, we aim to address a common bottleneck in the RL training system, i.e.,…