PulseAugur
EN
LIVE 17:07:34

New QUACK framework audits LLM agents for language grounding failures

By PulseAugur Editorial · [3 sources] ·

Researchers have introduced QUACK, an open-source environment and evaluation framework designed to audit the grounding of language used by Large Language Model (LLM) agents in multimodal social reasoning tasks. QUACK assesses agents on game outcomes, behavioral trajectories, and utterance-level consistency, specifically flagging issues like spatial hallucination and unsupported accusations. Evaluations of three frontier VLMs revealed significant grounding failures, with agents hallucinating over 15% of spatial claims and making over half of their accusations without evidence. AI

IMPACT This framework could lead to more robust LLM agents by identifying and correcting language grounding issues, improving their reliability in complex reasoning tasks.

RANK_REASON The cluster describes a new research paper introducing an evaluation framework for LLM agents.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

New QUACK framework audits LLM agents for language grounding failures

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster describes a new research paper introducing an evaluation framework for LLM agents.
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, safety, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
103 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [3]

  1. arXiv cs.AI TIER_1 English(EN) · Ye Yuan, Rui Song, Weien Li, Zeyu Li, Haochen Liu, Xiangyu Kong, Changjiang Han, Yonghan Yang, Zichen Zhao, Zixuan Dong, Fuyuan Lyu, Bowei He, Haolun Wu, Jikun Kang, Xue Liu ·

    QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

    arXiv:2605.27068v1 Announce Type: cross Abstract: Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most environments are scored only by game outcomes such as win…

  2. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Xue Liu ·

    QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

    Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most environments are scored only by game outcomes such as win rates and largely remain to text-only interaction…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

    A multimodal social reasoning environment and evaluation framework called QUACK is introduced to audit the grounding of agent language through three-level assessment of game outcomes, behavioral trajectories, and utterance-level consistency.

RELATED ENTITIES

RELATED TOPICS