arXiv AI
Learning to GUIDE the Group: Self-Learning LLM Facilitation Across Multi-Party Tasks
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 7
Interactive Learning for LLM Reasoning
arXiv:2509. 26306v5 Announce Type: replace Abstract: Existing multi-agent learning approaches have developed interactive training environments to explicitly promote collaboration among multiple Large Language Models (LLMs), thereby constructing stronger multi-agent systems (MAS).
arXiv AI
Oct 27
Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey
The article surveys evaluation methods for large language model (LLM)-based agents in multi-turn conversations, reviewing nearly 250 scholarly sources through a PRISMA-inspired framework. It introduces two taxonomies: one outlining what to evaluate—task completion, response quality, user experience, memory and context retention, planning, and tool integration—and another detailing how to evaluate, covering annotation-based, automated, hybrid, and self-judging approaches. The framework incorporates both traditional metrics like BLEU and ROUGE and advanced techniques suited to dynamic, interactive dialogues.
arXiv AI
Jul 7
Evaluating Generative Agents with Actions Grounded in Socially Distributed Task Environments using Incognita
arXiv:2607. 02975v1 Announce Type: new Abstract: Effective agency in social environments depends on when an agent seeks knowledge, when it acts, and whether its actions are justified by acquired information.
arXiv Machine Learning
Jun 5
CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
arXiv:2606. 05793v1 Announce Type: cross Abstract: While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging.
arXiv AI
Oct 12
Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses
The paper introduces Collaborative Theory of Mind (CToM), a framework that trains large language models to anticipate user responses and use those predictions to self‑revise before finalizing a reply. By combining a user‑response prediction objective with group‑relative policy optimization, CToM improves collaborative task performance across mathematical reasoning, coding, and writing tasks, raising accuracy from 74.1% to 79.6% on a math task and reducing the number of user replies needed. Ablation studies show that accurate user‑response predictions lead to more efficient interactions and better outcomes.
arXiv AI
Oct 2
Aligned but Not Partner-Specific: How Multimodal LLM Agents Succeed in Reference Games Without Forming Conceptual Pacts
The paper investigates whether multimodal large language model (LLM) agents form partner‑specific conceptual pacts during repeated reference games. By comparing real agent dyads with a novel pseudo‑dyad baseline that preserves task structure but removes shared partner history, the authors show that humans compress descriptions and align labels through entrainment, whereas agents produce verbose, fixed‑effort descriptions with near‑ceiling label overlap regardless of partner. Thus, LLMs succeed in coordination without forming compact, history‑dependent referring expressions typical of human dialogue.