Papers › Play to Generalize: Learning to Reason Through Game Play

Play to Generalize: Learning to Reason Through Game Play

9 Jun 2025arXiv:2506.08011archive 2025-07-28

Yunfei Xie, Yinsong Ma, Shiyi Lan, Alan Yuille, Junfei Xiao, Chen Wei

Developing generalizable reasoning capabilities in multimodal large language models (MLLMs) remains challenging. Motivated by cognitive science literature suggesting that gameplay promotes transferable cognitive skills, we propose a novel post-training paradigm, Visual Game Learning, or ViGaL, where MLLMs develop out-of-domain generalization of multimodal reasoning through playing arcade-like games. Specifically, we show that post-training a 7B-parameter MLLM via reinforcement learning (RL) on simple arcade-like games, e.g. Snake, significantly enhances its downstream performance on multimodal math benchmarks like MathVista, and on multi-discipline questions like MMMU, without seeing any worked solutions, equations, or diagrams during RL, suggesting the capture of transferable reasoning skills. Remarkably, our model outperforms specialist models tuned on multimodal reasoning data in multimodal reasoning benchmarks, while preserving the base model's performance on general visual benchmarks, a challenge where specialist models often fall short. Our findings suggest a new post-training paradigm: synthetic, rule-based games can serve as controllable and scalable pre-text tasks that unlock generalizable multimodal reasoning abilities in MLLMs.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2506.08011")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: official repository: 12 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yunfeixie233/vigal officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 0 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

12unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yunfeixie233/vigal. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

build_mathverse_gpt4_extract_prompt yunfeixie233/vigal/eval/mathverse/extract_calculate.py official repository unverified Apache-2.0 (permissive) · f8a7afabd4d22b07 · report
build_mathverse_gpt4_score_prompt yunfeixie233/vigal/eval/mathverse/extract_calculate.py official repository unverified Apache-2.0 (permissive) · 566d6789169e7b2c · report
can_infer_option yunfeixie233/vigal/eval/mathvision/extract_calculate.py official repository unverified Apache-2.0 (permissive) · e2935c878a3bfb63 · report
can_infer_text yunfeixie233/vigal/eval/mathvista/extract_calculate.py official repository unverified Apache-2.0 (permissive) · 59ef20be70813be5 · report
compute_approx_kl yunfeixie233/vigal/openrlhf/models/utils.py official repository unverified Apache-2.0 (permissive) · 95084b4b49902e3d · report
compute_reward yunfeixie233/vigal/openrlhf/models/utils.py official repository unverified Apache-2.0 (permissive) · 0d27f3b8c425d79f · report
convert_ring_attn_params yunfeixie233/vigal/openrlhf/models/ring_attn_utils.py official repository unverified Apache-2.0 (permissive) · 23c006771508ace1 · report
get_chat_response yunfeixie233/vigal/eval/mathverse/extract_calculate.py official repository unverified Apache-2.0 (permissive) · 2d84175fa37aa178 · report
get_chat_response yunfeixie233/vigal/eval/mathvision/extract_calculate.py official repository unverified Apache-2.0 (permissive) · 7b812ccf830749f3 · report
log_probs_from_logits yunfeixie233/vigal/openrlhf/models/utils.py official repository unverified Apache-2.0 (permissive) · 0612b61574b81472 · report
pad_sequences yunfeixie233/vigal/openrlhf/models/ring_attn_utils.py official repository unverified Apache-2.0 (permissive) · b26627fa753393a8 · report
reset_ring_attn_position_ids yunfeixie233/vigal/openrlhf/models/ring_attn_utils.py official repository unverified Apache-2.0 (permissive) · e93117d99aa6b210 · report

Tasks

Domain GeneralizationMathMultimodal ReasoningReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections