Copertina

Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Srivastava, Saksham Sahai
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MathDivide: Improved mathematical reasoning by large language models
di: Srivastava, Saksham Sahai, et al.
Pubblicazione: (2024)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
di: Srivastava, Saksham Sahai, et al.
Pubblicazione: (2025)

Dynamic Long Short-Term Memory Based Memory Storage For Long Horizon LLM Interaction
di: Lou, Yuyang, et al.
Pubblicazione: (2025)

Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations
di: Liu, Ziyang
Pubblicazione: (2026)

MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
di: Wang, Yuhui, et al.
Pubblicazione: (2026)

TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
di: Li, Kai, et al.
Pubblicazione: (2026)

Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
di: Li, Zaijing, et al.
Pubblicazione: (2024)

A Technical Survey of Reinforcement Learning Techniques for Large Language Models
di: Srivastava, Saksham Sahai, et al.
Pubblicazione: (2025)

UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
di: Luo, Haotian, et al.
Pubblicazione: (2025)

Preference-Aware Memory Update for Long-Term LLM Agents
di: Sun, Haoran, et al.
Pubblicazione: (2025)

CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
di: Wang, Yian, et al.
Pubblicazione: (2026)

MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
di: Zhou, Zijian, et al.
Pubblicazione: (2025)

Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
di: Hu, Chuanrui, et al.
Pubblicazione: (2026)

Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue
di: Lin, Jingjie, et al.
Pubblicazione: (2026)

HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
di: Hu, Mengkang, et al.
Pubblicazione: (2024)

MIRIX: Multi-Agent Memory System for LLM-Based Agents
di: Wang, Yu, et al.
Pubblicazione: (2025)

Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents
di: Tao, Dehao, et al.
Pubblicazione: (2026)

Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
di: Sun, Haoran, et al.
Pubblicazione: (2025)

AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
di: Jiayang, Cheng, et al.
Pubblicazione: (2026)

GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
di: Sun, Yushi, et al.
Pubblicazione: (2026)

Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
di: Shi, Yaorui, et al.
Pubblicazione: (2025)

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
di: Hu, Yuyang, et al.
Pubblicazione: (2026)

GTA: Generating Long-Horizon Tasks for Web Agents at Scale
di: Huang, Tenghao, et al.
Pubblicazione: (2026)

Milestone-Guided Policy Learning for Long-Horizon Language Agents
di: Wang, Zixuan, et al.
Pubblicazione: (2026)

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
di: Wan, Guangya, et al.
Pubblicazione: (2025)

IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling
di: Chen, Guoxin, et al.
Pubblicazione: (2025)

On the Structural Memory of LLM Agents
di: Zeng, Ruihong, et al.
Pubblicazione: (2024)

Enforcing Monotonic Progress in Legal Cross-Examination: Preventing Long-Horizon Stagnation in LLM-Based Inquiry
di: Liao, Hsien-Jyh
Pubblicazione: (2026)

Evaluating Very Long-Term Conversational Memory of LLM Agents
di: Maharana, Adyasha, et al.
Pubblicazione: (2024)

Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
di: Roy, Amartya, et al.
Pubblicazione: (2026)

ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agents
di: Zou, Huhai, et al.
Pubblicazione: (2026)

HorizonBench: Long-Horizon Personalization with Evolving Preferences
di: Li, Shuyue Stella, et al.
Pubblicazione: (2026)

ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning
di: Huang, Fan
Pubblicazione: (2026)

TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
di: Zhang, Xinliang Frederick, et al.
Pubblicazione: (2026)

S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
di: Su, Encheng, et al.
Pubblicazione: (2026)

REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
di: Chu, Zheng, et al.
Pubblicazione: (2026)

Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
di: Yang, Cheng, et al.
Pubblicazione: (2025)

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
di: Xi, Zhiheng, et al.
Pubblicazione: (2025)

AgentFold: Long-Horizon Web Agents with Proactive Context Management
di: Ye, Rui, et al.
Pubblicazione: (2025)

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation
di: Sun, Chenkai, et al.
Pubblicazione: (2025)