Copertina

When to Forget: A Memory Governance Primitive

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Simsek, Baris
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence I.2.6; I.2.11; H.3.3
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent Improvement
di: Shukla, Aaditya, et al.
Pubblicazione: (2025)

PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt Evolution
di: Shahmansoori, Arash
Pubblicazione: (2026)

Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation
di: Hasan, Md Toufique, et al.
Pubblicazione: (2025)

Memory as Metabolism: A Design for Companion Knowledge Systems
di: Miteski, Stefan
Pubblicazione: (2026)

When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees
di: Guo, Dongxin, et al.
Pubblicazione: (2026)

Understanding Multi-Agent LLM Frameworks: A Unified Benchmark and Experimental Analysis
di: Orogat, Abdelghny, et al.
Pubblicazione: (2026)

Decoding Fake Narratives in Spreading Hateful Stories: A Dual-Head RoBERTa Model with Multi-Task Learning
di: Bhaskar, Yash, et al.
Pubblicazione: (2025)

Procedural Game Level Design with Deep Reinforcement Learning
di: Özkan, Miraç Buğra
Pubblicazione: (2025)

Active Data
di: Arthur, Richard, et al.
Pubblicazione: (2026)

TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems
di: Seliuchenko, Volodymyr
Pubblicazione: (2026)

The 99% Success Paradox: When Near-Perfect Retrieval Equals Random Selection
di: Repantis, Vyzantinos, et al.
Pubblicazione: (2026)

Knowledge Equivalence in Digital Twins of Intelligent Systems
di: Zhang, Nan, et al.
Pubblicazione: (2022)

Drawing on Memory: Dual-Trace Encoding Improves Cross-Session Recall in LLM Agents
di: Stern, Benjamin, et al.
Pubblicazione: (2026)

Knowledge-Aware Iterative Retrieval for Multi-Agent Systems
di: Song, Seyoung
Pubblicazione: (2025)

ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation
di: Mittal, Tarun
Pubblicazione: (2026)

StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context
di: Annapureddy, Sasank, et al.
Pubblicazione: (2026)

A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web
di: Egami, Shusaku, et al.
Pubblicazione: (2026)

Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory
di: Jiang, Rongjie, et al.
Pubblicazione: (2026)

Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
di: Lauffer, Niklas, et al.
Pubblicazione: (2025)

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
di: Tang, Wenjie, et al.
Pubblicazione: (2026)

Agent-Based User-Adaptive Filtering for Categorized Harassing Communication
di: Rahaman, Zenefa, et al.
Pubblicazione: (2026)

When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines
di: Maryanskyy, Artem
Pubblicazione: (2026)

When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning
di: Kujur, Arahan
Pubblicazione: (2026)

Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure
di: Bottino, Federico, et al.
Pubblicazione: (2026)

Task Memory Engine: Spatial Memory for Robust Multi-Step LLM Agents
di: Ye, Ye
Pubblicazione: (2025)

Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
di: Costa, Rimom
Pubblicazione: (2025)

BudgetMem: Learning Selective Memory Policies for Cost-Efficient Long-Context Processing in Language Models
di: Alla, Chandra Vamsi Krishna, et al.
Pubblicazione: (2025)

Inferring Communities of Interest in Collaborative Learning-based Recommender Systems
di: Belal, Yacine, et al.
Pubblicazione: (2023)

One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents
di: Hong, Yoosung
Pubblicazione: (2026)

Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environment
di: Khouja, Aymen, et al.
Pubblicazione: (2026)

Governance-Aware Vector Subscriptions for Multi-Agent Knowledge Ecosystems
di: Johnson, Steven
Pubblicazione: (2026)

Extending NGU to Multi-Agent RL: A Preliminary Study
di: Hernandez, Juan, et al.
Pubblicazione: (2025)

MC-CPO: Mastery-Conditioned Constrained Policy Optimization
di: Olukola, Oluseyi, et al.
Pubblicazione: (2026)

The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
di: Pal, Biplab, et al.
Pubblicazione: (2026)

Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI
di: Pasupuleti, Vinil, et al.
Pubblicazione: (2026)

Dynamic Dual-Granularity Skill Bank for Agentic RL
di: Tu, Songjun, et al.
Pubblicazione: (2026)

FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
di: Zhang, Mingda, et al.
Pubblicazione: (2026)

How Good is ChatGPT in Giving Adaptive Guidance Using Knowledge Graphs in E-Learning Environments?
di: Ocheja, Patrick, et al.
Pubblicazione: (2024)

QTypeMix: Enhancing Multi-Agent Cooperative Strategies through Heterogeneous and Homogeneous Value Decomposition
di: Fu, Songchen, et al.
Pubblicazione: (2024)

Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
di: Ravindran, Santhosh Kumar
Pubblicazione: (2026)