analiza aiqbench
This research introduces Communication Policy Evolution (CPE), a framework that refines how autonomous LLM agents interact with users through text and UI without altering the underlying model weights. By formalizing communication strategies across different modalities, the study demonstrates that hybrid approaches leveraging both textual interaction for task performance and structured interfaces for response quality significantly improve agent success rates in proactive settings. The findings highlight information asymmetry management as a critical design dimension for future autonomous systems.
Communication Policy Evolution for Proactive LLM Agents
arXiv:2606.14314v1 Announce Type: new Abstract: LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.
Abstract:LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.
Artificial Intelligence (cs.AI)
arXiv:2606.14314 [cs.AI]
(or arXiv:2606.14314v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.14314 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 175 cuvinte
Subiecte conexe
Recovering topological information of light by topological learning
arXiv · 9 sept. 2026
Data driven approach for Outdoor Channel Prediction in 5G and Beyond
arXiv · 16 sept. 2026
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
arXiv · 1 sept. 2026
Non-monotonic population scaling and re-entrant photon number dynamics in the dissipative-pumped Tavis--Cummings model
arXiv · 9 iun. 2026