MARS: Memory-Enhanced Agents with Reflective Self-improvement
Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making, lack of long-term memory, and limited context windows in dynamic environments. To address these issues, this paper proposes an innovative framework Memory-Enhanced Agents with Reflective Self-improvement. The MARS framework comprises three agents: the User, the Assistant, and the Checker. By integrating iterative feedback, reflective mechanisms, and a memory optimization mechanism based on the Ebbinghaus forgetting curve, it significantly enhances the agents capabilities in handling multi-tasking and long-span information.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingSimilar Papers 제목 키워드 기반
Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-improving frameworks attempt to bridge thi…
MARS: Modular Agent with Reflective Search for Automated AI Research
A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model…
Self-evolving Agents with reflective and memory-augmented abilities
Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making. In this research, we propose a novel framework b…
Decision MakingParamMem: Augmenting Language Agents with Parametric Reflective Memory
Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various ap…
Multi-hop Question AnsweringMathematical ReasoningCode GenerationHonest Lying: Understanding Memory Confabulation in Reflexive Agents
Reflexion-style agents rely on self-generated reflections as memory, implicitly assuming that agents can accurately diagnose their own failures. We show that this assumption can fail systematically: across ALFWorld and H…