Imagen de Portada

Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Shiyan, Xia, Qifeng, Xia, Qiyun, Liu, Yisheng, Yu, Xinyu, Qu, Rui
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Multiagent Systems
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems
por: Moshkovich, Dany, et al.
Publicado: (2025)

Exposing Weak Links in Multi-Agent Systems under Adversarial Prompting
por: Arora, Nirmit, et al.
Publicado: (2025)

GAIR: GUI Automation via Information-Joint Reasoning and Group Reflection
por: Wei, Zishu, et al.
Publicado: (2025)

Beyond the Black Box: Interpretability of Agentic AI Tool Use
por: Tatsat, Hariom, et al.
Publicado: (2026)

ARMOR: An Agentic Framework for Reaction Feasibility Prediction via Adaptive Utility-aware Multi-tool Reasoning
por: Liu, Ye, et al.
Publicado: (2026)

PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization
por: Xiang, Dawei, et al.
Publicado: (2025)

Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts
por: Bo, Hongbo, et al.
Publicado: (2026)

SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search
por: Zhang, Yifan, et al.
Publicado: (2025)

The Effect of Belief Boxes and Open-mindedness on Persuasion
por: Bilgin, Onur, et al.
Publicado: (2025)

Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization
por: Li, Wenwu, et al.
Publicado: (2026)

Interpreting Emergent Extreme Events in Multi-Agent Systems
por: Tang, Ling, et al.
Publicado: (2026)

LinguistAgent: A Reflective Multi-Model Platform for Automated Linguistic Annotation
por: Li, Bingru
Publicado: (2026)

Aligning Artificial Superintelligence via a Multi-Box Protocol
por: Negozio, Avraham Yair
Publicado: (2025)

TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples
por: Xia, Shuren, et al.
Publicado: (2026)

SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation
por: Yang, Chengyi, et al.
Publicado: (2026)

Socratic RL: A Novel Framework for Efficient Knowledge Acquisition through Iterative Reflection and Viewpoint Distillation
por: Wu, Xiangfan
Publicado: (2025)

AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories
por: Xia, Xue, et al.
Publicado: (2026)

Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems
por: Chen, Ke, et al.
Publicado: (2025)

ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents
por: Xing, Sixue, et al.
Publicado: (2026)

Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization
por: Zhu, Ying, et al.
Publicado: (2025)

PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
por: Liu, Zihao, et al.
Publicado: (2025)

Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning
por: Kawabe, Tomoya, et al.
Publicado: (2026)

Conjunctive Prompt Attacks in Multi-Agent LLM Systems
por: Arif, Nokimul Hasan, et al.
Publicado: (2026)

Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration
por: Qu, Yun, et al.
Publicado: (2024)

AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
por: Ye, Yulei, et al.
Publicado: (2026)

LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual-Loop Edge-Terminal Collaboration
por: Qu, Zheyan, et al.
Publicado: (2025)

AI Agent Systems for Supply Chains: Structured Decision Prompts and Memory Retrieval
por: Yoshizato, Konosuke, et al.
Publicado: (2026)

Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems
por: Weckbecker, Moritz, et al.
Publicado: (2026)

City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification
por: Liu, Rui, et al.
Publicado: (2026)

MMCD: Multi-Modal Collaborative Decision-Making for Connected Autonomy with Knowledge Distillation
por: Liu, Rui, et al.
Publicado: (2025)

Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of Experience
por: Sayana, Krishna, et al.
Publicado: (2026)

Prompt Injection Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching
por: Gosmar, Diego, et al.
Publicado: (2026)

Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model Coordination
por: Dhrif, Hassen
Publicado: (2025)

Chameleon: Adaptive Adversarial Agents for Scaling-Based Visual Prompt Injection in Multimodal AI Systems
por: Zeeshan, M, et al.
Publicado: (2025)

Logical Robots: Declarative Multi-Agent Programming in Logica
por: Skvortsov, Evgeny, et al.
Publicado: (2026)

Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
por: Shen, Xu, et al.
Publicado: (2025)

TrafficGamer: Reliable and Flexible Traffic Simulation for Safety-Critical Scenarios with Game-Theoretic Oracles
por: Qiao, Guanren, et al.
Publicado: (2024)

Optimizing Cooperative path-finding: A Scalable Multi-Agent RRT* with Dynamic Potential Fields
por: Jiang, Jinmingwu, et al.
Publicado: (2019)

Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation
por: Liu, Binglin, et al.
Publicado: (2025)

Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization
por: Qu, Chengrui, et al.
Publicado: (2026)