# Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting

arXiv: https://arxiv.org/abs/2609.03923 · HTML: https://mlsanity.com/paper/2609.03923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 19 of 19)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [MeetingBank: A Benchmark Dataset for Meeting Summarization](https://mlsanity.com/paper/2305.17529/) (2023)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations](https://mlsanity.com/paper/2401.04883/) (2024)
- [Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system](https://mlsanity.com/paper/2307.15793/) (2023)
- [CiteAssist: A System for Automated Preprint Citation and BibTeX Generation](https://mlsanity.com/paper/2407.03192/) (2024)
- [Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection](https://mlsanity.com/paper/2510.01270/) (2025)
- [Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations](https://mlsanity.com/paper/2409.18602/) (2024)
- [Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization](https://mlsanity.com/paper/2410.14545/) (2024)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [Interaction Dynamics as a Reward Signal for LLMs](https://mlsanity.com/paper/2511.08394/) (2025)
- [MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf](https://mlsanity.com/paper/2502.04376/) (2025)
- [Humanlike Multi-user Agent (HUMA): Designing a Deceptively Human AI Facilitator for Group Chats](https://mlsanity.com/paper/2511.17315/) (2025)

## Abstract (arXiv)

In online meeting delegation, LLM agents fail to recognize when to speak. With no structured way to track stances, coverage, and floor, they miss the moments where they should contribute. Prompt-only delegates stay silent on 51.4% of the absent participant's talking opportunities on the AMI corpus. We present CAPA (Collaborative Agent Predictive Architecture), an architecture for online meeting delegation. A Perceiver updates the meeting state from each observed turn. A Predictor forecasts how the conversation will continue. A Controller decides whether to speak and which proposition to surface. A Generator phrases the chosen contribution in the participant's style. Two judges score the forecast and the action against the next observed turn. A Recalibrator updates the meeting state from those verdicts for future decisions. To evaluate online delegation, we introduce an episode-level protocol that scores whether, when, and what a delegate contributes around the participant's actual idea units. The protocol's schema-constrained LLM judges align with human annotations at Cohen's kappa = 0.71. On 137 AMI meetings, CAPA reduces the silence rate from 51.4% to 2.5%, doubles credited recovery (26.1 --> 52.2), and keeps hallucination at 0.6%. The failure mode shifts from omission to selection, with each residual near-miss attributable to a specific module of the architecture. Mechanism ablations identify the meeting state as the lever that closes the recognition gap, where raw-context scaling alone does not.