DraftFM: A FoundationModel for Day-Zero Drafting in Magic: The Gathering

• URL: http://arxiv.org/abs/2608.19568v1
• Date: Thu, 20 Aug 2026 02:13:23 GMT
• Title: DraftFM: A FoundationModel for Day-Zero Drafting in Magic: The Gathering
• Abstract summary: DraftFM scores every card available in the current pack conditioned on the drafted pool and the state of the draft.<n>A network fitted on 149 million human picks from 29 expansions predicts held-out picks in three expansions in their entirety.<n>The same architecture produced a card ranking for the then-unreleased set The Hobbit, sealed with its complete cryptographic provenance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Drafting a new Magic: The Gathering expansion begins before any pick from it has been observed: the complete card list is public, but the draft logs that supervised pick models train on do not yet exist. We study this day-zero regime directly. DraftFM is a discrete-choice policy that scores exactly the cards available in the current pack, conditioned on the drafted pool and the state of the draft. Every card enters as a frozen 775-dimensional function of its public card record, structured features and a fixed text embedding, with no card identities, set identities, or usage statistics anywhere in the model, so an unseen card is scored by the same machinery as a familiar one. A 1.6-million-parameter network fitted on 149 million human picks from 29 expansions predicts held-out picks in three expansions withheld in their entirety, reaching 50.8%, 60.4%, and 56.7% top-1 agreement, where uniform chance at the opening pick is about 7%. Refitted on all 32 observed expansions, the same architecture produced a card ranking for the then-unreleased set The Hobbit, sealed with its complete cryptographic provenance and published roughly 36 hours before the set became draftable on MTG Arena. The sealed ranking agrees with six independent expert reviewers roughly as much as those reviewers agree with one another. Evaluation against realized outcomes is committed to a follow-on note, whatever it shows.

Related papers

• WorldCup Arena: Prospective, Leakage-Free Evaluation of Frontier LLMs on a Live Tournament [1.4943316571343976]
  Six frontier LLMs were asked to fill in a seven-market prediction card for all 104 matches.<n>No answer existed when the question was asked, so the evaluation is leakage-free by construction.<n>What the tournament establishes is a set of behaviours the six systems share.
  arXiv  Detail & Related papers  (2026-08-04T17:59:55Z)
• When AI Writes, Who Gets Cited? Evidence of Citation Monoculture Across Language Models [45.91367912142692]
  We show that different models may still select the same narrow subset, producing citation monoculture without any single citation being wrong.<n>Eleven models from three vendors choose at most ten papers from uniformly random panels of thirty, with real titles and abstracts but fabricated authors, reassigned years, and hidden venues and citation counts.
  arXiv  Detail & Related papers  (2026-08-03T14:27:46Z)
• DarwinX: Evolving Agent Harnesses Through Natural Selection [48.64258219266629]
  DarwinX treats self-evolution as selection over a population of harnesses with the model frozen.<n>General agent competence, not benchmark-specific patches, so it survives changes of task, verifier, and base model.
  arXiv  Detail & Related papers  (2026-07-31T05:34:02Z)
• When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games [69.060029640261]
  We evaluate three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds.<n>Different models interpret announcements incompatibly, some as binding commitments and others as cheap talk.
  arXiv  Detail & Related papers  (2026-07-06T14:17:59Z)
• Predicting Drafted Deck Strength for "Magic: the Gathering" [16.700051324124143]
  Magic: the Gathering (MTG) exemplifies this setting, where the cards themselves define and alter gameplay rules, strategic constraints, and long-term outcomes.<n>We study Draft, a constrained deck-building format of MTG in which eight players make 39-45 sequential selections from semi-random packs to construct a 40-card deck under partial information.<n>We propose an encoder-based model that produces set-contextualized card embeddings to encode the draft decision sequence, with a consistent improvement over linear baselines on large-scale real-world data.
  arXiv  Detail & Related papers  (2026-07-06T08:12:35Z)
• Draft-OPD: On-Policy Distillation for Speculative Draft Models [49.23782868133977]
  Speculative decoding accelerates large language model inference by pairing a target model with a lightweight draft model whose proposed tokens are verified in parallel.<n>We propose Draft-OPD, which uses target-assisted rollout for stable continuations and replays drafting from the verification-exposed error positions.
  arXiv  Detail & Related papers  (2026-05-28T04:30:22Z)
• How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings [56.70440596502351]
  The past year has seen over 20 open document parsing models, yet benchmarks almost exclusively on OmniDocBench.<n>We present PureDocBench, a benchmark thatrenders document images from HTML/CSS, covering 10 domains, 66 pages, and 1,475 pages.
  arXiv  Detail & Related papers  (2026-05-08T09:30:31Z)
• The Leaderboard Illusion [61.27964089648608]
  Arena has emerged as the go-to leaderboard for ranking the most capable AI systems.<n>We identify systematic issues that have resulted in a distorted playing field.
  arXiv  Detail & Related papers  (2025-04-29T15:48:49Z)
• Learning With Generalised Card Representations for "Magic: The Gathering" [4.336779198334903]
  This work explores possible card representations that generalise to unseen cards. We study such representations based on numerical, nominal, and text-based features of cards, card images, and meta information about card usage from third-party services. Our results show that while the particular choice of generalised input representation has little effect on learning to predict human card selections among known cards, the performance on new, unseen cards can be greatly improved.
  arXiv  Detail & Related papers  (2024-07-08T12:42:44Z)
• Predicting Human Card Selection in Magic: The Gathering with Contextual Preference Ranking [0.0]
  We study drafting in the context of the card game Magic: The Gathering. We propose the use of a contextual preference network, which learns to compare two possible extensions of a given deck of cards. We demonstrate that the resulting network is better able to evaluate card decks in this game than previous attempts.
  arXiv  Detail & Related papers  (2021-05-25T12:07:27Z)
• Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search [33.23242783135013]
  State-of-the-art drafting methods fail to consider the multi-round nature of a MOBA 5v5 match series. We propose a novel drafting algorithm based on neural networks and Monte-Carlo tree search, named JueWuDraft. We demonstrate the practicality and effectiveness of JueWuDraft when compared to state-of-the-art drafting methods.
  arXiv  Detail & Related papers  (2020-12-18T11:19:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.