Paper Citation Record · LEDGER

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

As of 11 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 2 inbound Pith citation observations for arXiv:2508.21365.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2508.21365 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:23:27.591640Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T23:34:01.106317Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

42 of 42 outbound references displayed

verified exact6
verified fuzzy6
unresolved27
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 3462f19f-6220-49a1-a503-049fa24058ce · outbound

This paper cites Cause and Effect: Can Large Language Models Truly Understand Causality?.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Cause and Effect: Can Large Language Models Truly Understand Causality?

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-05T14:23:28.247417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6039e9bf-ca8c-441f-97b9-581a2cd2d618 · outbound

This paper cites an unresolved cited work.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:23.929458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b2c6e68-646a-43be-92f7-971cf3f8ff64 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.020818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65eeae8c-36e2-48ce-8939-8ceb51a810c7 · outbound

This paper cites MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.072935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a428987-6583-4222-9603-fb9898fd35bc · outbound

This paper cites Bayeschess: A computer chess program based on bayesian networks.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Bayeschess: A computer chess program based on bayesian networks

Reference 5

Resolution: verified exact; doi, observed 2026-08-05T14:23:28.080495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d4b144ae-8637-4860-883c-01ca553fd71a · outbound

This paper cites Font and Tobias Mahlmann.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Font and Tobias Mahlmann

Reference 6

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T14:23:29.926244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ce16c2fa-817c-4f36-9a6e-3bc437a6a1b5 · outbound

This paper cites Enabling self-improving agents to learn at test time with human-in-the-loop guidance.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Enabling self-improving agents to learn at test time with human-in-the-loop guidance

Reference 7

Resolution: verified exact; raw_fallback, observed 2026-08-05T14:23:29.665817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7bb921e6-e04c-48b4-83d7-f04eef122fb0 · outbound

This paper cites Measuring massive multitask language understanding.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Measuring massive multitask language understanding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.347757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 712a2b16-a84f-48c1-95db-a3c78fcec02a · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.434666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d97786b-a523-4a9f-a8cb-623b7b38872f · outbound

This paper cites A Survey on Large Language Model-Based Game Agents.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models A Survey on Large Language Model-Based Game Agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.473717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e15f8e-9e20-42f3-b515-e38236208f3f · outbound

This paper cites PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.541597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b120537f-e788-4299-b64b-8bc3f74f543e · outbound

This paper cites C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:23:30.920211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0a47fa39-e61c-4bd8-90a1-6ee078b5988d · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.667850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8d24579-c921-478d-a8ca-613a937f29ae · outbound

This paper cites Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoning.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-05T14:23:29.386562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a7266d34-80bb-40ec-a956-b4b069ea27d6 · outbound

This paper cites School chinese benchmark, 2018.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models School chinese benchmark, 2018

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:23:30.727816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4d0d153b-c670-4065-85c6-183d48962969 · outbound

This paper cites CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.911042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0e6f647-06ac-422b-be93-43d35f0c9b2e · outbound

This paper cites Simpo: Simple preference optimization with a reference-free reward.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Simpo: Simple preference optimization with a reference-free reward

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:24.975898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fe91552-3333-4fac-b23d-823e54708096 · outbound

This paper cites Playing Atari with Deep Reinforcement Learning.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Playing Atari with Deep Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:25.071210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad2ca66-1586-4690-931c-d94db8641ab5 · outbound

This paper cites Creating pro-level AI for a real-time fighting game using deep reinforcement learning.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Creating pro-level AI for a real-time fighting game using deep reinforcement learning

Reference 19

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T14:23:29.160079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 30ed4bd9-ea79-4473-95b0-6d637aab7769 · outbound

This paper cites Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, et al.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, et al

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:23:30.589098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cf1e4c3f-0971-4329-965f-2e2f5a9a7df6 · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Manning, Stefano Ermon, and Chelsea Finn

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:25.379171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e7b3ed-3fcd-47db-89ce-a6f1e284b427 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Proximal Policy Optimization Algorithms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:25.463390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad11b99-f8f3-4a63-b322-a6221a23776a · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:25.587387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5678c3e7-8d6f-494f-b41c-ad52a791efca · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:25.667622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e1d71b-d402-466c-a341-5baf90e30292 · outbound

This paper cites Mastering the game of go with deep neural networks and tree search.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Mastering the game of go with deep neural networks and tree search

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:25.840989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a01d5683-b46c-40b4-9454-fdbea02541dc · outbound

This paper cites Bayes' Bluff: Opponent Modelling in Poker.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Bayes' Bluff: Opponent Modelling in Poker

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:26.017512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb77aa2-f1af-4a39-8bb1-bc87abb3f955 · outbound

This paper cites Brown, Adam Santoro, Aditya Gupta, et al.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Brown, Adam Santoro, Aditya Gupta, et al

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:23:30.402090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8c0b0d61-6407-4193-b951-8fee35869ffe · outbound

This paper cites Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:26.207323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad54ce16-f332-43d9-82dd-ddde84dc1c39 · outbound

This paper cites Le, Ed H.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Le, Ed H

Reference 29

Resolution: malformed identifier; no resolver link, observed 2026-08-05T14:23:26.320509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cb96572-77c7-4a03-bca6-b78143d72d34 · outbound

This paper cites CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:26.402477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1d6f15b-32c1-4415-95b7-cce9431820eb · outbound

This paper cites StarCraft II: A New Challenge for Reinforcement Learning.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models StarCraft II: A New Challenge for Reinforcement Learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:26.486476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ec25b2f-cfd9-4b6c-a1f6-3fa2eeb994c4 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:26.587398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ef93714-881f-4b35-80d7-bf99c4f62fd2 · outbound

This paper cites Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:26.680923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f538ca5-df5c-4728-8f1e-c26e3ae4beff · outbound

This paper cites Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:26.747722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e3842a-54be-4d53-beb0-b66881e83778 · outbound

This paper cites Agents Play Thousands of 3D Video Games.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Agents Play Thousands of 3D Video Games

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:26.797595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dbef2c2-1c83-443d-93f3-8b5e6f3c6e76 · outbound

This paper cites Policy-to-language: Train llms to explain decisions with flow-matching generated rewards.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Policy-to-language: Train llms to explain decisions with flow-matching generated rewards

Reference 36

Resolution: verified exact; raw_fallback, observed 2026-08-05T14:23:28.595131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e6705ad7-3bbe-4ea4-a259-aaef503742f2 · outbound

This paper cites Mastering complex control in moba games with deep reinforcement learning.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Mastering complex control in moba games with deep reinforcement learning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:23:30.251013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 34de5102-2fc4-47ed-a428-202845f6c721 · outbound

This paper cites C har P oet: A C hinese classical poetry generation system based on token-free LLM.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models C har P oet: A C hinese classical poetry generation system based on token-free LLM

Reference 38

Resolution: verified exact; doi, observed 2026-08-05T14:23:27.806325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5a7d02ff-d198-40fd-88b0-c455de45c09f · outbound

This paper cites Training interactive agent in large fps game map with rule-enhanced reinforcement learning.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Training interactive agent in large fps game map with rule-enhanced reinforcement learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:23:30.097095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0aeb653d-cc59-49f5-ac7c-a1e24532cf66 · outbound

This paper cites Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:27.444486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4007ec55-0812-434b-9b84-7b42004e4305 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models Instruction-Following Evaluation for Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:27.530464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f49b6f6-5ae9-4788-8807-a56fc5849d5e · outbound

This paper cites PokerBench: Training Large Language Models to become Professional Poker Players.

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models PokerBench: Training Large Language Models to become Professional Poker Players

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T14:23:27.591640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 682ba848-7a4b-4e77-a5d3-b9c69669f7e6 · inbound

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application cites this paper.

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

Reference 288

Resolution: verified exact; arxiv_id, observed 2026-06-27T09:50:48.309200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f1e7d76b-4a07-474e-8ef8-18cc3018c509 · inbound

SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction cites this paper.

SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T23:34:01.106317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.