{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:58:58Z","timestamp":1775627938937,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/icmla66185.2025.00140","type":"proceedings-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:54:58Z","timestamp":1775591698000},"page":"936-941","source":"Crossref","is-referenced-by-count":0,"title":["MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs"],"prefix":"10.1109","author":[{"given":"Purbesh","family":"Mitra","sequence":"first","affiliation":[{"name":"University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,20742"}]},{"given":"Sennur","family":"Ulukus","sequence":"additional","affiliation":[{"name":"University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,20742"}]}],"member":"263","reference":[{"key":"ref1","author":"Guo","year":"2025","journal-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning"},{"key":"ref2","author":"Chen","year":"2025","journal-title":"Towards reasoning era: A survey of long chain-of-thought for reasoning large language models"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref4","author":"Snell","year":"2024","journal-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters"},{"key":"ref5","author":"Wang","year":"2024","journal-title":"Mixture-of-agents enhances large language model capabilities"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-8180-8_5"},{"key":"ref7","author":"Li","year":"2025","journal-title":"Rethinking mixture-of-agents: Is mixing different large language models beneficial?"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/pimrc62392.2025.11275145"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"ref10","author":"Liu","year":"2023","journal-title":"Lost in the middle: How language models use long contexts"},{"key":"ref11","author":"Jaech","year":"2024","journal-title":"Openai o1 system card"},{"key":"ref12","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref13","first-page":"101","author":"Munkhdalai","year":"2024","journal-title":"Leave no context behind: Efficient infinite context transformers with infini-attention"},{"key":"ref14","author":"Ye","year":"2025","journal-title":"Infinite retrieval: Attention enhanced llms in long-context processing"},{"key":"ref15","author":"Yan","year":"2025","journal-title":"Inftythink: Breaking the length limits of long-context reasoning in large language models"},{"key":"ref16","author":"Tian","year":"2025","journal-title":"Think twice: Enhancing llm reasoning by scaling multi-round test-time thinking"},{"key":"ref17","author":"Radha","year":"2024","journal-title":"Iteration of thought: Leveraging inner dialogue for autonomous large language model reasoning"},{"key":"ref18","author":"Goldie","year":"2025","journal-title":"Synthetic data generation & multi-step rl for reasoning & tool use"},{"key":"ref19","author":"Ning","year":"2025","journal-title":"Not all thoughts are generated equal: Efficient llm reasoning via multi-turn reinforcement learning"},{"key":"ref20","author":"Shao","year":"2024","journal-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models"},{"key":"ref21","author":"Cobbe","year":"2021","journal-title":"Training verifiers to solve math word problems"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","volume":"1","author":"Hu"},{"key":"ref23","author":"Hendrycks","year":"2021","journal-title":"Measuring mathematical problem solving with the math dataset"},{"key":"ref24","article-title":"Let\u2019s verify step by step","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lightman"},{"key":"ref25","first-page":"9","article-title":"Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions","volume":"13","author":"Li","year":"2024","journal-title":"Hugging Face repository"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref27","volume-title":"Granular format rewards for eliciting mathematical reasoning capabilities in small language models","author":"Brown","year":"2025"},{"key":"ref28","volume-title":"Unsloth","author":"Han","year":"2023"},{"key":"ref29","author":"Chen","year":"2021","journal-title":"Evaluating large language models trained on code"}],"event":{"name":"2025 International Conference on Machine Learning and Applications (ICMLA)","location":"Boca Raton, FL, USA","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Machine Learning and Applications (ICMLA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11471302\/11471304\/11471434.pdf?arnumber=11471434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:19:36Z","timestamp":1775625576000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icmla66185.2025.00140","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}