Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making | Paper Citation Record

Observation db279f33-f1da-4de9-bebe-eb88f9adbf2a · outbound

This paper cites Playing repeated games with Large Language Models.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Playing repeated games with Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.017569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fef9dd62-161a-4120-a068-400f4012eff3 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Gemini: A Family of Highly Capable Multimodal Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.109542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea23a2c-8123-48ce-9bcc-a0068d468113 · outbound

This paper cites The claude 3 model family: Opus, Sonnet, Haiku.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making The claude 3 model family: Opus, Sonnet, Haiku

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:53.040132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 314d2c1e-fe47-461d-8967-d2aaf269e71b · outbound

This paper cites Qwen Technical Report.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Qwen Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.356396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfa0c902-1e64-486a-b903-07848a6e5306 · outbound

This paper cites Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.446850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83f5384a-ad8f-40ea-8b5e-281b598fe90e · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Training Verifiers to Solve Math Word Problems

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.555958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd1758e4-3553-4f38-9474-fc54f9e18953 · outbound

This paper cites GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.645947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b185113e-c5d1-4ed8-be76-ccdb7e9470af · outbound

This paper cites DeepSeek-V3 Technical Report.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making DeepSeek-V3 Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.758530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2794b4f1-eeb1-45e2-bcbb-2ac90dc8244e · outbound

This paper cites GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.860130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d8a7c6b-1ad8-47b7-a6d7-b825f391e52c · outbound

This paper cites Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:45.977462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 800b13e8-4d5c-4992-80e0-4541f6923848 · outbound

This paper cites The Llama 3 Herd of Models.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.049369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d9e2ae1-2b13-4c2b-99b9-33d94cc15d0b · outbound

This paper cites Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-07T01:06:49.870672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1e557b64-bf58-4d69-8b69-b76e02d04dfa · outbound

This paper cites GameArena: Evaluating LLM Reasoning through Live Computer Games.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making GameArena: Evaluating LLM Reasoning through Live Computer Games

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.240151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5b849c8-3124-46be-8272-1958a5f11aab · outbound

This paper cites Towards Reasoning in Large Language Models: A Survey.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Towards Reasoning in Large Language Models: A Survey

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.349543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba95d4ab-71dc-4bd3-9418-a07a022a8bfc · outbound

This paper cites AvalonBench: Evaluating LLMs Playing the Game of Avalon.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making AvalonBench: Evaluating LLMs Playing the Game of Avalon

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.441264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 383cfab6-ec66-41b2-a9c9-3d1bf550e2ce · outbound

This paper cites AgentBench: Evaluating LLMs as Agents.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making AgentBench: Evaluating LLMs as Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.527722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3230912c-4691-4a6f-affc-ca9d5ac64acb · outbound

This paper cites Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.586498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65c861cc-6e06-49dc-963f-d45db9eeec59 · outbound

This paper cites Revisiting the Calibration of Modern Neural Networks.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Revisiting the Calibration of Modern Neural Networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.651932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92070451-fa98-406b-bdc5-23f3b49654cb · outbound

This paper cites What if Red Can Talk? Dynamic Dialogue Generation Using Large Language Models.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making What if Red Can Talk? Dynamic Dialogue Generation Using Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.740016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a9d2a0-70d7-44b4-9500-004750a86303 · outbound

This paper cites GPT-4 Technical Report.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making GPT-4 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.818457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfd239d8-cf7b-469c-999e-d555eab20673 · outbound

This paper cites The Effect of Sampling Temperature on Problem Solving in Large Language Models.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making The Effect of Sampling Temperature on Problem Solving in Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:46.907555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbf95857-d52e-4616-a7ee-becd2a568b4f · outbound

This paper cites MarioGPT: Open-Ended Text2Level Generation through Large Language Models.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making MarioGPT: Open-Ended Text2Level Generation through Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.023906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5216f9b0-8427-486f-b792-3fcd698f4a68 · outbound

This paper cites AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.117802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de3202ed-187d-423b-95af-579c94c86b8b · outbound

This paper cites Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.184068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e875a12b-cf14-455f-983a-bf187f305c84 · outbound

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

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.287212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27763c9e-edc1-48d5-abe3-84d74710dfc5 · outbound

This paper cites Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.379383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fdb686f-6b44-47a3-9e61-07d471ba029e · outbound

This paper cites Mistral 7B.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Mistral 7B

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.473661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61dc0e66-316b-4f9e-8fee-e5c1bc569072 · outbound

This paper cites Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.556176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfd151f6-18a4-4536-a0ba-07b7f651dc1c · outbound

This paper cites On the Frozen F-theory Landscape.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making On the Frozen F-theory Landscape

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-07T01:06:49.650209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1e094388-9dda-4c8f-9db6-94b317cb9dee · outbound

This paper cites MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.730350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87dce382-6a1b-4472-88f5-6469420f595c · outbound

This paper cites Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:47.818076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 527ad3c7-4f48-4004-a5f9-bdf6ccb7fb92 · outbound

This paper cites Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-07T01:06:49.501700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ea65a085-1154-413e-86be-bd21025d9ba1 · outbound

This paper cites On the volume of convolution bodies in the plane.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making On the volume of convolution bodies in the plane

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-07T01:06:49.406776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation acafd906-815f-41b2-811b-3f2c8be59549 · outbound

This paper cites LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:48.085801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64625d06-5580-43aa-84a2-e9c120d29099 · outbound

This paper cites The battlefield consists of 5 rows (corresponding to y-coordinates 0-4).

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making The battlefield consists of 5 rows (corresponding to y-coordinates 0-4)

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:52.893689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f0b2e13c-7773-4d78-9c48-c91499dd509b · outbound

This paper cites Human units are placed on the left side of the battlefield, remain stationary, and attack approaching enemies.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Human units are placed on the left side of the battlefield, remain stationary, and attack approaching enemies

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:52.749361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c028a988-8f2b-4e73-83a1-b0c1bf9e13fa · outbound

This paper cites Defending units fire bullets or activate skills to attack enemies.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Defending units fire bullets or activate skills to attack enemies

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:52.586135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b81768cf-3b83-482e-834e-8cac2d7e5fcd · outbound

This paper cites Placing a new unit in an occupied cell is not allowed.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Placing a new unit in an occupied cell is not allowed

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:52.435311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 55c7ce57-13bf-45d4-9d1a-8aa5882f8eb7 · outbound

This paper cites If a unit’s health drops to 0, it is eliminated and removed from the battlefield.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making If a unit’s health drops to 0, it is eliminated and removed from the battlefield

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:52.250295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e901168c-15bd-495f-a0e7-09db75830f9c · outbound

This paper cites If any enemy successfully reaches the left side of the battlefield, the player loses.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making If any enemy successfully reaches the left side of the battlefield, the player loses

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:52.050709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 95c07d1d-3b38-4a3e-b2b6-f066b28d1a8e · outbound

This paper cites Gold characters cost three times as much as bronze characters, but their stats (attack, health, numerical skill effects, etc.) are twice as high.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Gold characters cost three times as much as bronze characters, but their stats (attack, health, numerical skill effects, etc.) are twice as high

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:51.861430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 097ae285-a9f8-4c6e-a4c4-a6c8aed27e01 · outbound

This paper cites If both sides have the same number of characters, the invader attacks first.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making If both sides have the same number of characters, the invader attacks first

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:51.690917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e662124b-105b-44fb-b95c-384ec7d6f719 · outbound

This paper cites an unresolved cited work.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:06:51.480602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f10f3028-fd45-4d34-b325-c13d4ed087d7 · outbound

This paper cites However, if there are Taunt minions on the opponent’s side, attackers must prioritize attacking them.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making However, if there are Taunt minions on the opponent’s side, attackers must prioritize attacking them

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:51.335745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d009285b-90c3-43d8-8d0e-ce61b8cf1ab9 · outbound

This paper cites an unresolved cited work.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:06:51.191096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dad4fe38-e777-4cd0-b626-22b500187732 · outbound

This paper cites A.2.2 Invader units Unit Attributes FireLizard Attack: 2, Health: 2, Cost: 1, Ability: Deals 2 damage to the enemy that killed it upon death.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making A.2.2 Invader units Unit Attributes FireLizard Attack: 2, Health: 2, Cost: 1, Ability: Deals 2 damage to the enemy that killed it upon death

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:50.976355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cd290fc0-05d2-44c4-af2d-6b11fef7d50a · outbound

This paper cites Each faction consists of three characters.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Each faction consists of three characters

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:50.801852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ac745349-2c9c-4fee-8737-614746a7e60c · outbound

This paper cites In each round, the three Invader characters act first in order, followed by the three Defender characters.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making In each round, the three Invader characters act first in order, followed by the three Defender characters

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:50.622299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 08fd9254-f16e-4de8-8c93-28b74e0e046d · outbound

This paper cites On each turn, a character uses the next skill in their list and continues cycling through them in order.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making On each turn, a character uses the next skill in their list and continues cycling through them in order

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:50.480265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9098988c-7836-419b-9817-423b500e47cc · outbound

This paper cites Light and Dark counter each other with 1.5× damage.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making Light and Dark counter each other with 1.5× damage

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:50.326721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2af913c9-e727-4979-866a-7697738ec073 · outbound

This paper cites A.3.2 Invader skills 15 Skill Name Description Fire Skills flame_splash Deals 12 damage and applies Burning for 2 rounds (1 layer, 5 damage per round).

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making A.3.2 Invader skills 15 Skill Name Description Fire Skills flame_splash Deals 12 damage and applies Burning for 2 rounds (1 layer, 5 damage per round)

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:50.173728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3781921d-0e50-40bd-b726-d4c3ebb973d1 · outbound

This paper cites B.1 Rule violation Rate (RVR) This metric measures how often a model’s initial strategy proposal fails to adhere to the game’s explicit rules, particularly budget constraints.

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making B.1 Rule violation Rate (RVR) This metric measures how often a model’s initial strategy proposal fails to adhere to the game’s explicit rules, particularly budget constraints

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:50.022346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers