The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Learning to Reason and Memorize with Self-Notes
Open accessAbstract
Large language models have been shown to struggle with multi-step reasoning, and do not retain previous reasoning steps for future use. We propose a simple method for solving both of these problems by allowing the model to take Self-Notes. Unlike recent chain-of-thought or scratchpad approaches, the model can deviate from the input context at any time to explicitly think and write down its thoughts. This allows the model to perform reasoning on the fly as it reads the context and even integrate previous reasoning steps, thus enhancing its memory with useful information and enabling multi-step reasoning. Experiments across a wide variety of tasks demonstrate that our method can outperform chain-of-thought and scratchpad methods by taking Self-Notes that interleave the input text.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
HiAgent manages working memory through subgoal-based chunks, and Self-Notes enhance reasoning with intermediate notes.
“HiAgent (Hu et al., 2024) manages working memory through subgoalbased chunks, and Self-Notes (Lanchantin et al., 2023) enhance reasoning with intermediate notes.”
From RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory (2025) · cites this paper as Lanchantin et al., 2023
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
RoFormer: Enhanced transformer with rotary position embedding
Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., & Liu, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2023.127063 · Cited by 1,957
Toolformer: Language Models Can Teach Themselves to Use Tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv · doi:10.48550/arxiv.2302.04761 · Cited by 1,150
Flagged first, then by citations
Research works printed but not linked: 43
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention Is All You Need. In NeurIPS, 2017.
- Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language Models are Few-Shot Learners. In NeurIPS, 2020.
- Maxwell Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, Charles Sutton, and Augustus Odena. Show Your Work: Scratchpads for Intermediate Computation with Language Models. arXiv, abs/2112.00114, 2021. · arXiv
- Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In NeurIPS, 2022.
- Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712, 2023. · arXiv
- Jacob Austin, Augustus Odena, Maxwell I. Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie J. Cai, Michael Terry, Quoc V. Le, and Charles Sutton. Program Synthesis with Large Language Models. arXiv, abs/2108.07732, 2021. · arXiv
- Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A. Smith, and Mike Lewis. Measuring and Narrowing the Compositionality Gap in Language Models. arXiv:2210.03350, abs/2210.03350, 2022. · arXiv
- Antonia Creswell, Murray Shanahan, and Irina Higgins. Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning. In ICLR, 2023.
- E. Zelikman, Yuhuai Wu, and Noah D. Goodman. STaR: Bootstrapping Reasoning With Reasoning. In NeurIPS, 2022.
- Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, Pierre Sermanet, Noah Brown, Tomas Jackson, Linda Luu, Sergey Levine, Karol Hausman, and Brian Ichter. Inner Monologue: Embodied Reasoning through Planning with Language Models. In CoRL, 2022.
- Angela Fan, Thibaut Lavril, Edouard Grave, Armand Joulin, and Sainbayar Sukhbaatar. Ad- dressing Some Limitations of Transformers with Feedback Memory. arXiv, 2020.
- Da Ju, Stephen Roller, Sainbayar Sukhbaatar, and Jason Weston. Staircase Attention for Recurrent Processing of Sequences. In NeurIPS, 2022.
- DeLesley Hutchins, Imanol Schlag, Yuhuai Wu, Ethan Dyer, and Behnam Neyshabur. Block- Recurrent Transformers. In NeurIPS, 2022.
- Paul van den Broek, Mary Jane White, Panayiota Kendeou, and Sarah Carlson. Reading between the lines. Developmental and individual differences in cognitive processes in reading comprehension. In. K. Wagner, C. Schatschneider, & C. Plythian-Sence (Eds.), Beyond decoding: The behavioral and biological foundations of reading comprehension, pages 107-123, 2009.
- Cem Anil, Yuhuai Wu, Anders Andreassen, Aitor Lewkowycz, Vedant Misra, Vinay Ramasesh, Ambrose Slone, Guy Gur-Ari, Ethan Dyer, and Behnam Neyshabur. Exploring Length General- ization in Large Language Models. In NeurIPS, 2022.
- Shubham Toshniwal, Sam Wiseman, Karen Livescu, and Kevin Gimpel. Chess as a Testbed for Language Model State Tracking. In AAAI, 2022.
- Subhro Roy and Dan Roth. Solving general arithmetic word problems. arXiv preprint arXiv:1608.01413, 2016. · arXiv
- Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Jacob Hilton, Reiichiro Nakano, Christo- pher Hesse, and John Schulman. Training verifiers to solve math word problems. ArXiv, abs/2110.14168, 2021. · arXiv
- Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, et al. HuggingFace's Trans- formers: State-of-the-art Natural Language Processing. In EMNLP: System Demonstrations, 2020.
- Jason Weston, Antoine Bordes, Sumit Chopra, and Tomas Mikolov. Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks. In ICLR, 2016.
- Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023. · arXiv
- Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, and Rob Fergus. End-to-End Memory Networks. NeurIPS, 2015.
- Mikael Henaff, Jason Weston, Arthur Szlam, Antoine Bordes, and Yann LeCun. Tracking the world state with recurrent entity networks. arXiv preprint arXiv:1612.03969, 2016. · arXiv
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT, 2019.
- Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit, and Lukasz Kaiser. Uni- versal Transformers. In ICLR, 2019.
- Oana-Maria Camburu, Tim Rocktäschel, Thomas Lukasiewicz, and Phil Blunsom. e-SNLI: Natural Language Inference with Natural Language Explanations. In NeurIPS, 2018.
- Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. Program induction by ratio- nale generation: Learning to solve and explain algebraic word problems. arXiv preprint arXiv:1705.04146, 2017. · arXiv
- Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. Large Language Models are Zero-Shot Reasoners. In NeurIPS, 2022.
- H. Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. arXiv, abs/2212.10509, 2022. · arXiv
- Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, et al. Do As I Can, Not As I Say: Grounding Language in Robotic Affordances. arXiv:2204.01691, 2022. · arXiv
- Ofir Press, Noah Smith, and Mike Lewis. Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation. In ICLR, 2022.
- Shun Kiyono, Sosuke Kobayashi, Jun Suzuki, and Kentaro Inui. SHAPE: Shifted Absolute Position Embedding for Transformers. In EMNLP, 2021.
- Dieuwke Hupkes, Verna Dankers, Mathijs Mul, and Elia Bruni. Compositionality decomposed: How do neural networks generalise? In IJCAI, 2020.
- Koustuv Sinha, Amirhossein Kazemnejad, Siva Reddy, Joelle Pineau, Dieuwke Hupkes, and Adina Williams. The Curious Case of Absolute Position Embeddings. Findings of EMNLP, 2022.
- Alex Graves. Adaptive Computation Time for Recurrent Neural Networks. arXiv:1603.08983, 2016. · arXiv
- Tolga Bolukbasi, Joseph Wang, Ofer Dekel, and Venkatesh Saligrama. Adaptive Neural Networks for Efficient Inference. In ICML, 2017.
- Andrea Banino, Jan Balaguer, and Charles Blundell. PonderNet: Learning to Ponder. In ICML Workshop on Automated Machine Learning, 2021.
- Timo Schick, Jane Dwivedi-Yu, Zhengbao Jiang, Fabio Petroni, Patrick Lewis, Gautier Izac- ard, Qingfei You, Christoforos Nalmpantis, Edouard Grave, and Sebastian Riedel. PEER: A Collaborative Language Model. In ICLR, 2023.
- Jiatao Gu, Changhan Wang, and Junbo Zhao. Levenshtein Transformer. NeurIPS, 2019.
- Mitchell Stern, William Chan, Jamie Kiros, and Jakob Uszkoreit. Insertion Transformer: Flexible Sequence Generation via Insertion Operations. In ICML, 2019.
- Ahmed Elgohary, Denis Peskov, and Jordan Boyd-Graber. Can You Unpack That? Learning to Rewrite Questions-in-Context. In EMNLP-IJCNLP, 2019.
- Gangwoo Kim, Sungdong Kim, Kang Min Yoo, and Jaewoo Kang. Generating Information- Seeking Conversations from Unlabeled Documents. In EMNLP, 2022.
- Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. PaLM: Scaling Language Modeling with Pathways. arXiv:2204.02311, 2022. · arXiv
Cited by
Sorted by citations
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
Liu, J., Kong, Z., Yang, C., Yang, F., Li, T., Dong, P., Nanjekye, J., Tang, H., Yuan, G., Niu, W., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.04903
Metadata
- Authors
- Lanchantin, J., Toshniwal, S., Weston, J., Szlam, A., & Sukhbaatar, S.
- ORCID
- Lanchantin, Jack
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 11891-11911
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133237984
- Cited by
- 9
- References
- 2
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 1 · 2023: 1
- FWCI
- 9.59
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- cc-by
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Social Sciences › Psychology › Developmental and Educational Psychology › Innovative Teaching and Learning Methods
- Life Sciences › Neuroscience › Cognitive Neuroscience › Memory Processes and Influences
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Visual and Cognitive Learning Processes
- Keywords
- self-explanation, reasoning, memorization, metacognition, learning strategies
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
