paper-with-me

홈 › Papers

Field-Theoretic Memory for AI Agents: Continuous Dynamics for Context Preservation

2026-01-31 · Subhadip Mitra arxiv

We present a memory system for AI agents that treats stored information as continuous fields governed by partial differential equations rather than discrete entries in a database. The approach draws from classical field theory: memories diffuse through semantic space, decay thermodynamically based on importance, and interact through field coupling in multi-agent scenarios. We evaluate the system on two established long-context benchmarks: LoCoMo (ACL 2024) with 300-turn conversations across 35 sessions, and LongMemEval (ICLR 2025) testing multi-session reasoning over 500+ turns. On LongMemEval, the field-theoretic approach achieves significant improvements: +116% F1 on multi-session reasoning (p<0.01, d= 3.06), +43.8% on temporal reasoning (p<0.001, d= 9.21), and +27.8% retrieval recall on knowledge updates (p<0.001, d= 5.00). Multi-agent experiments show near-perfect collective intelligence (>99.8%) through field coupling. Code is available at github.com/rotalabs/rotalabs-fieldmem.

📄 PDF Abstract BibTeX arXiv:2602.21220

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Discrete Versus Continuous Algorithms in Dynamics of Affective Decision Making

2023-09-01 · V. I. Yukalov, E. P. Yukalova

The dynamics of affective decision making is considered for an intelligent network composed of agents with different types of memory: long-term and short-term memory. The consideration is based on probabilistic affective…

Decision Making

On the Convergence of Model Free Learning in Mean Field Games

2019-07-04 · Romuald Elie, Julien Pérolat, Mathieu Laurière, Matthieu Geist 외

Learning by experience in Multi-Agent Systems (MAS) is a difficult and exciting task, due to the lack of stationarity of the environment, whose dynamics evolves as the population learns. In order to design scalable algor…

Reinforcement Learning

Game-theoretical control with continuous action sets

2014-12-01 · Steven Perkins, Panayotis Mertikopoulos, David S. Leslie

Motivated by the recent applications of game-theoretical learning techniques to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous ac…

Reinforcement Learning

Modern Hopfield Networks with Continuous-Time Memories

2025-02-14 · Saul Santos, António Farinhas, Daniel C. McNamee, André F. T. Martins

Recent research has established a connection between modern Hopfield networks (HNs) and transformer attention heads, with guarantees of exponential storage capacity. However, these models still face challenges scaling st…

Learning non-Markovian Dynamical Systems with Signature-based Encoders

2025-09-15 · Eliott Pradeleix, Rémy Hosseinkhan-Boucher, Alena Shilova, Onofrio Semeraro 외 arxiv

Neural ordinary differential equations offer an effective framework for modeling dynamical systems by learning a continuous-time vector field. However, they rely on the Markovian assumption - that future states depend on…

Continuous Control