By reusing validated function-level KV caches (stitching) and regenerating only localized error spans (patching), FCGraft makes CodeLLM policies for embodied agents faster and more robust than prompt-level caching.
Think Before You Act: Decision Transformers with Working Memory
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training. As a result, training on a new task may deteriorate the model's performance on previous tasks. In contrast to LLMs' implicit memory mechanism, the human brain utilizes distributed memory storage, which helps manage and organize multiple skills efficiently, mitigating the forgetting phenomenon. Inspired by this, we propose a working memory module to store, blend, and retrieve information for different downstream tasks. Evaluation results show that the proposed method improves training efficiency and generalization in Atari games and Meta-World object manipulation tasks. Moreover, we demonstrate that memory fine-tuning further enhances the adaptability of the proposed architecture.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A stepwise planner with memory-guided execution and evaluation raises ScienceWorld scores to 67.4, outperforming CLIN and published SOTA baselines.
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
citing papers explorer
-
Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
By reusing validated function-level KV caches (stitching) and regenerating only localized error spans (patching), FCGraft makes CodeLLM policies for embodied agents faster and more robust than prompt-level caching.
-
One STEP at a time: Language Agents are Stepwise Planners
A stepwise planner with memory-guided execution and evaluation raises ScienceWorld scores to 67.4, outperforming CLIN and published SOTA baselines.
-
The Rise and Potential of Large Language Model Based Agents: A Survey
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.