Instruction

Large language models (LLMs) have achieved remarkable success, yet they face significant challenges in logical and symbolic reasoning. This is because (i) learning syntax, semantics, and world knowledge through tasks such as next-word prediction or masked language modeling does not ensure the logical reasoning ability of LLMs, and (ii) the pre-training corpora of LLMs primarily consist of human-written texts, which lack high-quality logical reasoning samples such as logical deduction and proofs. This two-day bridge program aims to thoroughly explore and expand the intersection of AI and Logic, with special interest in logical and symbolic reasoning in language models. This would improve the reasoning capabilities of LLMs to solve complex logical problems requiring sophisticated deductive, inductive, or abductive reasoning, and to avoid producing responses that contradict themselves across multiple relevant questions.

Topics

Topics of interest include, but are not limited to:

• • Logical question answering of LLMs;

  • Chain-of-thought reasoning of LLMs;

  • External tool-use (e.g., logic solvers) for LLM reasoning;

  • Logical consistency of LLMs (e.g., implication, negation);

  • Symbolic expressions and reasoning of LLMs;

  • Multi-turn interactions for LLM reasoning;

  • Multi-agent LLMs’ reasoning;

  • Benchmarks and evaluation for logical reasoning of LLMs;

  • Relevant topics from logic, linguistics, and cognitive science.

Important Dates

• First-Round Submission Deadline: October 31, 2025

• First-Round Notification of Acceptance: November 14, 2025

• Second-Round Submission Deadline: December 5, 2025   December 13, 2025

• Second-Round Notification of Acceptance: December 20, 2025    December 25, 2025

All deadlines are specified in Anywhere on Earth (AoE).

Attendence

The bridge program is open to researchers, practitioners, and industry professionals interested in logical and symbolic reasoning of language models. There are no specific criteria or maximum number of attendees.

Format of the Bridge

This is a two-day bridge program with no restrictions on attendance. The bridge program is organized to include keynote presentations of invited speakers, panel discussion, tutorials, oral paper presentations, and poster sessions.

Program Schedule

January 20th, 2026

9:00am – 9:05am Welcome Remarks

9:05am – 9:20am Oral 1: DiLA: Enhancing LLM Tool Learning with Differential Logic Layer 

9:20am – 9:35am Oral 2: Do LLMs Really Struggle at NL-FOL Translation? Revealing their Strengths via a Novel Benchmarking Strategy

9:35am – 10:15am Keynote 1: Logical Reasoning in Large Language Models by Hanmeng Liu (Hainan University)

10:15am – 10:30am Oral 3: Abductive State Grounding For Neuro-Symbolic Reinforcement Learning

10:30am – 11:00am   Break (Poster Session 1)

11:00am – 11:40am Keynote 2: Empowering Large Language Models with Reliable Logical Reasoning by Liangming Pan (Peking University)

11:40am – 12:15pm Tutorial (Logical Consistency)

12:15pm – 12:30pm Oral 4: $\Delta_1$–LLM: Symbolic–Neural Integration for Credible and Explainable Reasoning

12:30pm – 2:00pm  Lunch (on your own; no sponsored lunch provided)

(Poster Session 2)

2:00pm – 2:15pm  Oral 5: A Study on the Reasoning Ability of LLMs Using Negation Principles in Chinese Sentences

2:15pm – 2:30pm  Oral 6: Tracing and Correcting Programs: Critic-Guided Synthesis for Visual Reasoning

2:30pm – 3:10pm Keynote 3: Neuro-Symbolic Learning in the Era of Large Models by Lan-Zhe Guo (Nanjing University)

3:10pm – 3:25pm  Oral 7: MuSLR: Multimodal Symbolic Logical Reasoning

3:30pm – 4:00pm  Break (Poster Session 3)

4:00pm – 5:00pm    Panel

January 21th, 2026

9:00am – 9:05am Welcome Remarks

9:05am – 9:20am Oral 8: Tracking the Evolution of Multimodal Reasoning on Visual Puzzles

9:20am – 9:35am Oral 9: SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios

9:35am – 10:15am Keynote 4: Can We Teach Logical Reasoning to LLMs? An Approach Using Principled Synthetic Corpora by Terufumi Morishita (Central Research Laboratory of Hitachi, ltd.)

10:15am – 10:30am Oral 10: Neuro-Symbolic AI for Alzheimer's Disease: Physics-Informed Biomarker Prediction and Verifiable Intervention Planning

10:30am – 11:00am   Break (Poster Session 4)

11:00am – 11:40am Huawei Celia Logic Intelligence Progress & Challenge by Wai Ming Tai (Celia Team)

11:40am – 12:15pm Tutorial (Logical QA)

12:15pm – 12:30pm Oral 11: Where Do Weights Come From? Weighting and Weighing by LLMs and Formal Argumentation in Discretionary Judicial Reasoning

12:30pm – 2:00pm  Lunch (on your own; no sponsored lunch provided)

(Poster Session 5)

2:00pm – 2:15pm  Oral 12:  Logical-SAGE: A Logical Socratic Architecture for Guided Evolution in Neuro-Symbolic Reasoning

2:15pm – 2:55pm  Keynote 5: Reasoning and Generalization of Language Models by Yue Zhang (Westlake University)

2:55pm – 3:30pm  Keynote 6: X-A-Castle: Integrating Structured Causal Knowledge for Better Reasoning by Keli Zhang (Noah’s Ark Laboratory)

3:30pm – 4:00pm  Break (Poster Session 6)

4:00pm – 5:00pm    Panel

Poster Schedule

January 20, 9:00am-11:00am

• WS131: Quantitative Modeling of Recommendation Systems Driven by Dynamic Preference Logic

    Jianming Sun, Shuo Yang, Bing Zhang, Zheng Dequan, Jie Piao

• WS132: Evolutionary System 2 Reasoning: An Empirical Proof

Zeyuan Ma, Huang Wenqi, Guo-Huan Song, Hongshu Guo, Sijie Ma, Zhiguang Cao, Yue-Jiao Gong

• WS133: The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in Closed-Source and Open-Source Models on Multimodal Puzzles

Vernon Toh, Yew Ken Chia, Deepanway Ghosal, Soujanya Poria

• WS134: Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity

Subramanyam Sahoo, Vinija Jain, Rui Min, Saanidhya Vats, Siddharth Mohapatra, Aman Chadha, Divya Chaudhary

• WS135: AgentSHAP: Interpreting LLM Agent Tool Importance with Monte Carlo Shapley Value Estimation

Miriam Horovicz

• WS136: Neuro-Symbolic Resolution of Recommendation Conflicts in Multimorbidity Clinical Guidelines

Shiyao Xie

• WS137: Evaluating Autoformalization Robustness via Semantically Similar Paraphrasing

Hayden Moore, Asfahan Shah

• WS138: Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn’t

Quy-Anh Dang, Chris Ngo

• WS139: ChaosBench-Logic: A Benchmark for Logical and Symbolic Reasoning on Chaotic Dynamical Systems

Noel Thomas

• WS140: A Logical Characterization of Filter Bubbles under Personalized Feeds

Lei Li, Jialiang Yan

January 20, 11:00am-2:00pm

• WS131: SOKRATES: Distilling Symbolic Knowledge into Option-Level Reasoning via Solver-Guided Preference Optimization

Zhaoxiang Feng, David Scott Lewis

• WS132: Tracing and Correcting Programs: Critic-Guided Synthesis for Visual Reasoning

Marha Midhatiey Rusli, Donghyeon Shin, Sejin Kim, Sundong Kim

• WS133: Abductive State Grounding For Neuro-Symbolic Reinforcement Learning

Min-Le Su, Kai-Yu Chen, Jiong-Da Wang, Yikuan Hu, Wang-Zhou Dai

• WS134: LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning

Yu Zhu, Kai Yang

• WS135: Self-Aligned Reward: Towards Effective and Efficient Reasoners

Peixuan Han, ADIT KRISHNAN, Gerald Friedland, Jiaxuan You, Luyang Kong

• WS136: Structural-Semantic Constraints for Enhanced Chinese Language Modeling

Zhongyi Deng

• WS137: Consistent Biases in Large Language Models' Syllogistic Reasoning

Limeng Ge

• WS138: Steering LLM Interactions Using Persona Vectors

Shrey Jha, Akhil Upadrasta, Vivian How, Hriday Narang, Aaron Z. Reed

• WS139: Integrating Reflective Equilibrium and Structured Argumentation: A Logical Approach to Norm Identification

Tianwen Xu, Jieting Luo

• WS140: From Logical Mismatch to Logical Alignment：The Integration of the Logic of Evidential Reasoning and the Logic of Multi-Agent Collaboration Framework

Jiawen Zhang, Jinze Sang, Chenggong Zhao, Juan Li, Jianzhong Shi

January 20, 2:00pm-5:00pm

• WS131: Glass-Box Arbitrators: An Explainable Neuro-Symbolic AI Framework for International Commercial Arbitration Proceedings

David Scott Lewis, Haley Yi

• WS132: Operationalising Ethical Principles in Planning with Large Language Models

Tammy Zhong, Yang Song, Maurice Pagnucco

• WS133: TableNet: A Large-Scale Table Dataset with LLM-Powered Autonomous Generation

Ruilin Zhang, Kai Yang

• WS134: Distilling Neural Knowledge into Interpretable Belief Rule Bases

XINLEI CAO, Pengsen Liu, Jun Liu, Bilal Ahmed Lodhi, Dongqiang Yang, Yunan Liu, Peng Su, Li Zou, Peng Shi

• WS135: Reintegrating Classification into the Concept of Analogy

Liying Zhang

• WS136: Beyond Translation: A Decomposed Collaborative Reasoning Framework Harnessing LLMs and Symbolic Solvers

Zhixin Zhang, Shaobo Zhang, Chengcan Wu, Meng Sun

• WS137: SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios

Weidong Zhan, Yue Wang, Nan Hu, Liming Xiao, Jingyuan Ma, Yuhang Qin, Zheng Li, Yixin Yang, Sirui Deng, Jinkun Ding, Qingxiu Dong, Wenhan Ma, Rui Li, Weilin Luo, Qun Liu, Zhifang Sui 

• WS138: Toward Honest Language Models for Deductive Reasoning

Jiarui Liu, Kaustubh Dhole, Yingheng Wang, Haoyang Wen, Sarah Zhang, Haitao Mao, Gaotang Li, Neeraj Varshney, Jingguo Liu, Xiaoman Pan

• WS139: See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay

Ashish Baghel, Paras Chopra

• WS140: $\Delta_1$–LLM: Symbolic–Neural Integration for Credible and Explainable Reasoning

Yang Xu, Jun Liu, Shuwei Chen, Chris Nugent, Hailin Guo

January 21, 9:00am-11:00am

• WS131: Logical-SAGE: A Logical Socratic Architecture for Guided Evolution in Neuro-Symbolic Reasoning

Jinlong Tian, Jiang Yu, Kewei Cheng, Yue He, Yunfei Wang, Huibin Tan, Haotian Wang, Wenjing Yang, Shixuan Liu

• WS132: Axiomatic Negation Coherence in Language Models: Evidence from FOLIO

Md Muntaqim Meherab, Naimur Rahman

• WS133: DiLA: Enhancing LLM Tool Learning with Differential Logic Layer

Yu Zhang, Hui-Ling Zhen, Zehua Pei, Yingzhao Lian, Lihao Yin, Mingxuan Yuan, Bei Yu

• WS134: From Logical Mismatch to Logical Alignment：The Integration of the Logic of Evidential Reasoning and the Logic of Multi-Agent Collaboration Framework

Jiawen Zhang, Jinze Sang, Chenggong Zhao, Juan Li, Jianzhong Shi

• WS135: LLMs for Game Theory: Entropy-Guided In-Context Learning and Adaptive CoT Reasoning

Tommaso Felice Banfi, Sashenka Gamage

• WS136: Dynamic Rationality of Many-Valued Judgment Aggregation: Implications for Multi-Agent LLM Reasoning

Jiahong Wang

• WS137: Evaluating LLMs on Syllogistic Reasoning: A Human–Model Accuracy Comparison under Premise Order Effects

Yuqi Ding, Yiming Zhang, Yanmei Gu, Guoping Du, Junbo Zhao

• WS138: Conversation as Belief Revision: GreedySAT Revision for Global Logical Consistency in Multi-Turn LLM Dialogues

Sanjan Baitalik, Rajashik Datta, Amit Kumar Das, Sruti Das Choudhury

• WS139: A Study on the Reasoning Ability of LLMs Using Negation Principles in Chinese Sentences

LI Ran, Lingxiang Fan, Gan Ze, Zhaoyang Gao, Lifei Wang, Renjia Xiao, Zhe Yu, Guiyun Zhao, Zhe Lin

• WS140: LogicFlow: Integrating Symbolic Deduction and Gradient-Based Reasoning in Large Language Models

Maowei Jiang, Qi Wang, Yifan WANG, Peter Búš, Zhang Wenyan, Hongliang Niu, Yusong Hu

January 21, 11:00am-2:00pm

• WS131: Event-State Semantics: The Formal Semantics of English Temporal Sentences

Zhang Wenyan, Zhang Kai, Zhou Beihai, Dong Su, Hao Lin

• WS132: SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning

Ali Asgarov, Umid Suleymanov, Aadyant Khatri

• WS133: Graph-Based Exploration for ARC-AGI-3 Interactive Reasoning Tasks

Evgenii Rudakov, Jonathan P. Shock, Benjamin Ultan Cowley

• WS134: A Logical Approach to Interpret Neural Network: Formalizing Hopfield Network Dynamics

Xiaoxuan Fu, Ke Wu

• WS135: MuSLR: Multimodal Symbolic Logical Reasoning

Jundong Xu, Hao Fei, Yuhui Zhang, Liangming Pan, Qijun Huang, Qian Liu, Preslav Nakov, Min-Yen Kan, William Yang Wang, Mong-Li Lee, Wynne Hsu

• WS136: Do LLMs Really Struggle at NL-FOL Translation? Revealing their Strengths via a Novel Benchmarking Strategy

Andrea Brunello, Luca Geatti, Michele Mignani, Angelo Montanari, Nicola Saccomanno

• WS137: Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives

Aheli Poddar, Saptarshi Sahoo, Sujata Ghosh

• WS138: Hypothesis Generation via LLM-Automated Language Bias for ILP

Yang Yang, Jiemin Wu, Yutao Yue

• WS139: Graph of Thoughts Nanobiomaterials Assistants: Towards Logical, Tool-Augmented, and Multi-Agent Reasoning in Scientific LLMs

Xianghang Peng, David Scott Lewis

• WS140: PlantPhenoLM: Phenotype-Genotype Mapping Inference with Multi-Turn LLM Reasoning and Selective Prediction

Rajashik Datta, Sanjan Baitalik, Amit Kumar Das, Sruti Das Choudhury

January 21, 2:00pm-5:00pm

• WS131: An LLM-Assisted Belief Rule Base Model for Explainable Decision Classification

Lixian Xu, Jun Liu, Aftab Ali, Li Zou, Dehu Yu, Peng Shi

• WS132: FaST-3D: Integrating Fast and Slow Thinking for 3D Visual Question Answering

Yuhang Liu, Boyi Sun, Yuzheng Hu, Jing Yang, Yutong Wang, Fei-Yue Wang

• WS133: The Path of Least Resistance: Guiding LLM Reasoning Trajectories with Prefix Consensus

Ishan Jindal, Sai Prashanth Akuthota, Jayant Taneja, SACHIN DEV SHARMA

• WS134: Explain the Why: A Dual-Layer Interpretable Framework for Mental Health Detection

Bo Yuan, Yulin Chen

• WS135: Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning

Sahil Rajesh Dhayalkar

• WS136: Graph-Based Exploration for ARC-AGI-3 Interactive Reasoning Tasks

Evgenii Rudakov, Jonathan P. Shock, Benjamin Ultan Cowley

• WS137: Where Do Weights Come From? Weighting and Weighing by LLMs and Formal Argumentation in Discretionary Judicial Reasoning

Davide Liga, Réka Markovich, Liuwen Yu

• WS138: Hierarchical Multi-Agent Orchestration for Enhanced Logical Reasoning in Large Language Models

Naina Chaturvedi, Ananda Gunawardena

• WS139: Cross-Domain Analogical Reasoning via Structural Logic Transfer in Multi-Agent Scientific Discovery Systems

Panos Skouras

• WS140: Neuro-Symbolic AI for Alzheimer's Disease: Physics-Informed Biomarker Prediction and Verifiable Intervention Planning

David Scott Lewis, Enrique Zueco

Bridge Contact: aaai.2026.lmreasoning@gmail.com