Elamur Research⌕
☰
home / papers / 2026 / Semantic-Aware Logical Reasoning via a Semiotic Framework

Semantic-Aware Logical Reasoning via a Semiotic Framework

Paper · 2026 · Yunyao Zhang, Xinglang Zhang, Junxi Sheng et al.

Summary

LLM logical reasoning methods usually assume clean predicates and unambiguous contexts. They handle logical depth but ignore semantic difficulty: abstract concepts, shifting definitions and opposing stances. The authors propose LogicAgent, a framework built on Greimas' Semiotic Square, recast in first-order logic (FOL). It adds an existential import check and a three-valued scheme (True/False/Uncertain).

For each target proposition, the agent works in three stages:

  1. Semantic structuring: it builds a contradiction, a contrary and the contrary's negation, checked with a CFG-based parser.
  2. Logical reasoning: it translates the premises into FOL, plans the deduction and solves it.
  3. Reflective verification: it reconciles the outcomes for each variant, using the square's implication relations when results conflict or stay undecided.

The authors also release RepublicQA, a human-validated benchmark. It draws on abstract philosophical propositions paired with systematically built contrary and contradictory forms.

LogicAgent sets a new state of the art on RepublicQA and transfers well to standard logic benchmarks. The work matters because it shows that modelling meaning-level oppositions, not just formal structure, makes LLM reasoning more robust.

Key points

  • LogicAgent improves on strong baselines by 6.25% on average on RepublicQA across backbone models. It gains a further 7.05% on average across ProntoQA, ProofWriter, FOLIO and ProverQA.
  • RepublicQA outscores prior benchmarks on all five semantic complexity indicators. Its readability sits at college level (FKGL = 11.94).
  • On RepublicQA, accuracy drops from 0.4286 to 0.0000 as reasoning depth grows from 4 to 6 hops, while FKGL climbs from 12.99 to 17.70. In the other benchmarks, semantic difficulty stays roughly constant across hops.
  • In the efficiency ablation, removing planning cuts processing time the most (−37.1%), and removing FOL cuts it by 35.4%. The full pipeline is costlier than single-pass methods.
  • Code is available at github.com/AI4SS/Logic-Agent.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Huazhong University of Science and TechnologyWuhan · China59 works · 8,310 citations🎓La Trobe UniversityMelbourne · Australia2 works · 269 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,685 works

Cite

Cite as Yunyao Zhang, Xinglang Zhang, Junxi Sheng, Wenbing Li, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang and Zikai Song. 2026. Semantic-Aware Logical Reasoning via a Semiotic Framework. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.835

@inproceedings{zhang2026semantic,
  title = {{Semantic-Aware Logical Reasoning via a Semiotic Framework}},
  author = {Yunyao Zhang, Xinglang Zhang, Junxi Sheng, Wenbing Li, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang and Zikai Song},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.835},
  url = {https://doi.org/10.18653/v1/2026.acl-long.835}
}

References

75 references, 27 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Aristoteles and Hippocrates G Apostle. 1966. Aristotle’s metaphysics. Indiana University Press Bloomington, EUA. find
  3. Steven Bird. 2006. Nltk: the natural language toolkit. In Proceedings of the COLING/ACL 2006 interactive presentation sessions, pages 69–72.
  4. Guangyao Chen, Siwei Dong, Yu Shu, Ge Zhang, Jaward Sesay, Börje F Karlsson, Jie Fu, and Yemin Shi. 2023. Autoagents: A framework for automatic agent generation. arXiv preprint arXiv:2309.17288.
  5. Michael Cohen, Badri Vellambi, and Marcus Hutter. 2020. Asymptotically unambitious artificial general intelligence. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 2467– 2476. find
  6. Yangruibo Ding, Jinjun Peng, Marcus Min, Gail Kaiser, Junfeng Yang, and Baishakhi Ray. 2024. Semcoder: Training code language models with comprehensive semantics reasoning. Advances in Neural Information Processing Systems, 37:60275–60308. find
  7. Zane Durante, Qiuyuan Huang, Naoki Wake, Ran Gong, Jae Sung Park, Bidipta Sarkar, Rohan Taori, Yusuke Noda, Demetri Terzopoulos, Yejin Choi, and 1 others. 2024. Agent ai: Surveying the horizons of multimodal interaction. arXiv preprint arXiv:2401.03568. — [arXiv:2401.03568](https://arxiv.org/abs/2401.03568) find
  8. Ben Eisner, Yi Yang, Todor Davchev, Mel Vecerik, Jonathan Scholz, and David Held. 2024. Deep se (3)-equivariant geometric reasoning for precise placement tasks. arXiv preprint arXiv:2404.13478. — [arXiv:2404.13478](https://arxiv.org/abs/2404.13478) find
  9. Sicheng Feng, Gongfan Fang, Xinyin Ma, and Xinchao Wang. 2025a. Efficient reasoning models: A survey. arXiv preprint arXiv:2504.10903.
  10. Sicheng Feng, Song Wang, Shuyi Ouyang, Lingdong Kong, Zikai Song, Jianke Zhu, Huan Wang, and Xinchao Wang. 2025b. Can mllms guide me home? a benchmark study on fine-grained visual reasoning from transit maps. arXiv preprint arXiv:2505.18675. — [arXiv:2505.18675](https://arxiv.org/abs/2505.18675) find
  11. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Pal: Program-aided language models. In International Conference on Machine Learning, pages 10764–10799. PMLR. find
  12. Edward Gibson. 1998. Linguistic complexity: Locality of syntactic dependencies. Cognition, 68(1):1–76. find
  13. Algirdas Julien Greimas. 1987. On meaning: Selected writings in semiotic theory. (No Title). find
  14. Algirdas Julien Greimas. 1988. Maupassant: The semiotics of text. find
  15. Algirdas Julien Greimas, Joseph Courtés, Larry Crist, and Daniel Patte. 1982. Semiotics and language: An analytical dictionary. Indiana University Press Bloomington. find
  16. Gaole He, Gianluca Demartini, and Ujwal Gadiraju. 2025. Plan-then-execute: An empirical study of user trust and team performance when using llm agents as a daily assistant. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pages 1–22. find
  17. Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, and 1 others. 2023. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 3(4):6.
  18. Yangliu Hu, Zikai Song, Na Feng, Yawei Luo, Junqing Yu, Yi-Ping Phoebe Chen, and Wei Yang. 2025. Sf2t: Self-supervised fragment finetuning of video-llms for fine-grained understanding. arXiv preprint arXiv:2504.07745. — [arXiv:2504.07745](https://arxiv.org/abs/2504.07745) find
  19. Shiting Huang, Zhen Fang, Zehui Chen, Siyu Yuan, Junjie Ye, Yu Zeng, Lin Chen, Qi Mao, and Feng Zhao. 2025. Critictool: Evaluating self-critique capabilities of large language models in tool-calling error scenarios. arXiv preprint arXiv:2506.13977.
  20. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  21. Terence Irwin and 1 others. 2019. Nicomachean ethics. Hackett Publishing. find
  22. Ugo Dal Lago. 2009. Context semantics, linear logic, and computational complexity. ACM Transactions on Computational Logic (TOCL), 10(4):1–32. find
  23. Ernest Lepore and Matthew Stone. 2007. Logic and semantic analysis. In Philosophy of Logic, pages 173–204. Elsevier. find
  24. Mengdi Li, Jiaye Lin, Xufeng Zhao, Wenhao Lu, Peilin Zhao, Stefan Wermter, and Di Wang. 2025. Curriculum-rlaif: Curriculum alignment with reinforcement learning from ai feedback. arXiv preprint arXiv:2505.20075. find
  25. Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752. find
  26. Wenbing Li, Hang Zhou, Junqing Yu, Zikai Song, and Wei Yang. 2024. Coupled mamba: Enhanced multimodal fusion with coupled state space model. arXiv preprint arXiv:2405.18014. find
  27. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948.
  28. Jacky Liang, Wenlong Huang, Fei Xia, Peng Xu, Karol Hausman, Brian Ichter, Pete Florence, and Andy Zeng. 2023. Code as policies: Language model programs for embodied control. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 9493–9500. IEEE. find
  29. Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, and 1 others. 2022. Folio: Natural language reasoning with first-order logic. arXiv preprint arXiv:2209.00840.
  30. Yaobo Liang, Chenfei Wu, Ting Song, Wenshan Wu, Yan Xia, Yu Liu, Yang Ou, Shuai Lu, Lei Ji, Shaoguang Mao, and 1 others. 2024. Taskmatrix.ai: Completing tasks by connecting foundation models with millions of apis. Intelligent Computing, 3:0063. find
  31. Jiaye Lin, Yifu Guo, Yuzhen Han, Sen Hu, Ziyi Ni, Licheng Wang, Mingguang Chen, Hongzhang Liu, Ronghao Chen, Yangfan He, and 1 others. 2025. Se-agent: Self-evolution trajectory optimization in multi-step reasoning with llm-based agents. arXiv preprint arXiv:2508.02085. — [arXiv:2508.02085](https://arxiv.org/abs/2508.02085) find
  32. Xueqi Ma, Shuo Yang, Yanbei Jiang, Shu Liu, Zhenzhen Liu, Jiayang Ao, Xingjun Ma, Sarah Monazam Erfani, and James Bailey. 2026. Attention in space: Functional roles of vlm heads for spatial reasoning. arXiv preprint arXiv:2603.20662. — [arXiv:2603.20662](https://arxiv.org/abs/2603.20662) find
  33. Abulhair Saparov and He He. 2022. Language models are greedy reasoners: A systematic formal analysis of chain-of-thought. arXiv preprint arXiv:2210.01240.
  34. Yuhao Shen, Tianyu Liu, Junyi Shen, Jinyang Wu, Quan Kong, Li Huan, and Cong Wang. 2026. Double: Breaking the acceleration limit via double retrieval speculative parallelism. Preprint, arXiv:2601.05524. find
  35. Peter Smith. 2003. An introduction to formal logic. Cambridge University Press. find
  36. Mohammad Reza Ghasemi Madani, Soyeon Caren Han, Shuo Yang, and Jey Han Lau. 2026. Inclusion-of-thoughts: Mitigating preference instability via purifying the decision space. Preprint, arXiv:2604.04944. — [arXiv:2604.04944](https://arxiv.org/abs/2604.04944) find
  37. Zikai Song, Run Luo, Lintao Ma, Ying Tang, Yi-Ping Phoebe Chen, Junqing Yu, and Wei Yang. 2025. Temporal coherent object flow for multi-object tracking. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 6978–6986. find
  38. Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, and Mehrdad Farajtabar. 2024. Gsm-symbolic: Understanding the limitations of mathematical reasoning in large language models. arXiv preprint arXiv:2410.05229.
  39. Zikai Song, Ying Tang, Run Luo, Lintao Ma, Junqing Yu, Yi-Ping Phoebe Chen, and Wei Yang. 2024. Au-togenic language embedding for coherent point tracking. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 2021–2030. find
  40. Liangming Pan, Alon Albalak, Xinyi Wang, and William Yang Wang. 2023. Logic-lm: Empowering large language models with symbolic solvers for faithful logical reasoning. arXiv preprint arXiv:2305.12295.
  41. Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang, and Xinchao Wang. 2026. Hypergraph-state collaborative reasoning for multi-object tracking. Preprint, arXiv:2604.12665. — [arXiv:2604.12665](https://arxiv.org/abs/2604.12665) find
  42. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. find
  43. Hongda Sun, Weikai Xu, Wei Liu, Jian Luan, Bin Wang, Shuo Shang, Ji-Rong Wen, and Rui Yan. 2024. Determlr: Augmenting llm-based logical reasoning from indeterminacy to determinacy. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pag… find
  44. Nisarg Patel, Mohith Kulkarni, Mihir Parmar, Aashna Budhiraja, Mutsumi Nakamura, Neeraj Varshney, and Chitta Baral. 2024. Multi-logieval: Towards evaluating multi-step logical reasoning ability of large language models. arXiv preprint arXiv:2406.17169.
  45. Oyvind Tafjord, Bhavana Dalvi Mishra, and Peter Clark. 2020. Proofwriter: Generating implications, proofs, and abductive statements over natural language. arXiv preprint arXiv:2012.13048.
  46. Shishir G Patil, Tianjun Zhang, Xin Wang, and Joseph E Gonzalez. 2024. Gorilla: Large language model connected with massive apis. Advances in Neural Information Processing Systems, 37:126544–126565.
  47. Richard W Paul. 2013. Critical and reflective thinking: A philosophical perspective. In Dimensions of thinking and cognitive instruction, pages 445–494. Routledge. find
  48. C Plato. 2016. The republic. In Democracy: A Reader, pages 229–233. Columbia University Press. find
  49. Chengwen Qi, Ren Ma, Bowen Li, He Du, Binyuan Hui, Jinwang Wu, Yuanjun Laili, and Conghui He. 2025. Large language models meet symbolic provers for logical reasoning evaluation. arXiv preprint arXiv:2502.06563. — [arXiv:2502.06563](https://arxiv.org/abs/2502.06563) find
  50. Hyun Ryu, Gyeongman Kim, Hyemin S Lee, and Eunho Yang. 2024. Divide and translate: Compositional first-order logic translation and verification for complex logical reasoning. arXiv preprint arXiv:2410.08047. — [arXiv:2410.08047](https://arxiv.org/abs/2410.08047) find
  51. David Tuggy. 1993. Ambiguity, polysemy, and vagueness. find
  52. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30.
  53. Bingbing Wang, Zhixin Bai, Qianlong Wang, Jingjie Lin, Min Yang, Xi Zeng, and Ruifeng Xu. 2025. More than just a conversation: A multi-agent reasoning graph knowledge distillation for conversational stance detection. In Proceedings of the 48th International ACM SIGIR Conference on Research and Devel… find
  54. Ke Wang, Houxing Ren, Aojun Zhou, Zimu Lu, Sichun Luo, Weikang Shi, Renrui Zhang, Linqi Song, Mingjie Zhan, and Hongsheng Li. 2023. Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning. arXiv preprint arXiv:2310.03731.
  55. Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Cheng Jiayang, Chunkit Chan, and Yangqiu Song. 2024. CANDLE: Iterative conceptualization and instantiation distillation from large language models for commonsense reasoning. In Proceedin… find
  56. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171.
  57. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824– 24837.
  58. Jinyang Wu, Shuo Yang, Changpeng Yang, Yuhao Shen, Shuai Zhang, Zhengqi Wen, and Jianhua Tao. 2026. Spark: Strategic policy-aware exploration via dynamic branching for long-horizon agentic learning. Preprint, arXiv:2601.20209.
  59. Jundong Xu, Hao Fei, Meng Luo, Qian Liu, Liangming Pan, William Yang Wang, Preslav Nakov, Mong-Li Lee, and Wynne Hsu. 2024a. Aristotle: Mastering logical reasoning with a logic-complete decompose-search-resolve framework. arXiv preprint arXiv:2412.16953.
  60. Jundong Xu, Hao Fei, Liangming Pan, Qian Liu, Mong-Li Lee, and Wynne Hsu. 2024b. Faithful logical reasoning via symbolic chain-of-thought. arXiv preprint arXiv:2405.18357.
  61. An Yang, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoyan Huang, Jiandong Jiang, Jianhong Tu, Jianwei Zhang, Jingren Zhou, and 1 others. 2025a. Qwen2. 5-1m technical report. arXiv preprint arXiv:2501.15383. — Qwen2.5-1M Technical Report
  62. Shuo Yang, Caren Han, Siwen Luo, and Eduard Hovy. 2025b. Magic-vqa: Multimodal and grounded inference with commonsense knowledge for visual question answering. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16967– 16986. find
  63. Yuan Yang, Siheng Xiong, Ali Payani, Ehsan Shareghi, and Faramarz Fekri. 2023. Harnessing the power of large language models for natural language to first-order logic translation. arXiv preprint arXiv:2305.15541. find
  64. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, 36:11809–11822. find
  65. Liliang Ye, Yunyao Zhang, Yafeng Wu, Yi-Ping Phoebe Chen, Junqing Yu, Wei Yang, and Zikai Song. 2025. Mvp: Winning solution to smp challenge 2025 video track. arXiv preprint arXiv:2507.00950. — [arXiv:2507.00950](https://arxiv.org/abs/2507.00950) find
  66. Xiang Zhang, Juntai Cao, Jiaqi Wei, Chenyu You, and Dujian Ding. 2025a. Why prompt design matters and works: A complexity analysis of prompt search space in llms. arXiv preprint arXiv:2503.10084. find
  67. Xinglang Zhang, Yunyao Zhang, ZeLiang Chen, Junqing Yu, Wei Yang, and Zikai Song. 2026a. Logical phase transitions: Understanding collapse in llm logical reasoning. Preprint, arXiv:2601.02902.
  68. Yifan Zhang, Jingqin Yang, Yang Yuan, and Andrew Chi-Chih Yao. 2023. Cumulative reasoning with large language models. arXiv preprint arXiv:2308.04371.
  69. Yunyao Zhang, Yihao Ai, Zuocheng Ying, Qirui Mi, Junqing Yu, Wei Yang, and Zikai Song. 2026b. Coupling macro dynamics and micro states for long-horizon social simulation. Preprint, arXiv:2604.05516. — [arXiv:2604.05516](https://arxiv.org/abs/2604.05516) find
  70. Yunyao Zhang, Zikai Song, Hang Zhou, Wenfeng Ren, Yi-Ping Phoebe Chen, Junqing Yu, and Wei Yang. 2025b. ga − s 3 : Comprehensive social network simulation with group agents. In Findings of the Association for Computational Linguistics: ACL 2025, pages 8950–8970, Vienna, Austria. Association for Comp… find
  71. Zhuosheng Zhang, Yuwei Wu, Hai Zhao, Zuchao Li, Shuailiang Zhang, Xi Zhou, and Xiang Zhou. 2020. Semantics-aware bert for language understanding. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 9628–9635. find
  72. Hongyu Zhao, Kangrui Wang, Mo Yu, and Hongyuan Mei. 2023a. Explicit planning helps language models in logical reasoning. arXiv preprint arXiv:2303.15714. find
  73. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, and 1 others. 2023b. A survey of large language models. arXiv preprint arXiv:2303.18223, 1(2).
  74. Zi’ou Zheng, Christopher Malon, Martin Renqiang Min, and Xiaodan Zhu. 2024. Exploring the role of reasoning structures for constructing proofs in multi-step natural language reasoning with large language models. arXiv preprint arXiv:2410.08436. find
  75. Keyang Zhong, Junlin Xie, Hefeng Wu, Haofeng Li, and Guanbin Li. 2026. Collaborative multi-agent scripts generation for enhancing imperfect-information reasoning in murder mystery games. Preprint, arXiv:2604.11741.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-semantic-aware-logical-reasoning-semiotic/