Metraipolis › archive › dc_39bc096f2fdb

PUBG Ally: A Conversational Embodied Agent as an AI Teammate — arXiv:2609.29837

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29837
License (as archived)
CC0-1.0
Archived
2026-10-08T04:26:23.254Z
SHA-256 of the archived text
5655639d5e3f4c2735fc039767bcfe27b61aa4acc1b346bf300f03834bff8843
Stable URL of this page
https://metraipolis.com/documento/dc_39bc096f2fdb

How to cite

PUBG Ally: A Conversational Embodied Agent as an AI Teammate — arXiv:2609.29837 — arXiv (en), https://arxiv.org/abs/2609.29837 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_39bc096f2fdb (Metraipolis archive dc_39bc096f2fdb, sha256 5655639d5e3f4c2735fc039767bcfe27b61aa4acc1b346bf300f03834bff8843)
BibTeX
@misc{dc39bc096f2fdb,
  title = {PUBG Ally: A Conversational Embodied Agent as an AI Teammate — arXiv:2609.29837},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29837},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_39bc096f2fdb; sha256 5655639d5e3f4c2735fc039767bcfe27b61aa4acc1b346bf300f03834bff8843},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29837. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency constraints while interacting naturally with players, keeping its speech synchronized with its actions. Ally therefore combines agentic tool use with real-time game control. A language-model agent uses a controlled interface to inspect game information, interpret player speech, maintain context, decide what to say, and issue high-level action choices that steer a faster control layer for movement, combat, and recovery. Because the player's and Ally's speech and actions continually shape each other and the course of the match, training requires data from actual gameplay. We therefore collect data across nearly 39k sessions in which real players play alongside Ally, recording gameplay, player speech, agent decisions, tool use, actions, and player feedback, and use these records for iterative training. To evaluate teammate quality, we use player feedback and preference comparisons to identify gaps between offline evaluations and player preferences, and iteratively refine the evaluation criteria. Deploying Ally in live service further requires low-latency on-device execution and safeguards for player-facing communication, which we address through model compression, context compaction, targeted safety training, runtime guardrails, and memory redaction. During the live service, we surveyed players in 141 countries. Among respondents whose play with Ally was confirmed in game records, positive responses exceeded negative responses by 25.1 percentage points when asked whether they would recommend Ally, with players describing Ally not only as a tool but also as a teammate or companion.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.29837 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T03:50:57.839Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).