FloCA: Towards Faithful and Logically Consistent Flowchart Reasoning

arXiv:2602.14035 · cs.AI · Submitted 2026-02-15 · Read on arXiv

cs.AI

Submitted: 2026-02-15

Updated: 2026-09-29

Comments: Accepted to the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)

Code: https://github.com/Jinzi-Zou/FloCA-flowchart-reasoning

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Grounding — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 4 episodes

Sources

• A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
• VERUS-LM: a Versatile Framework for Combining LLMs with Symbolic Reasoning
• LLM-Based Repair of Static Nullability Errors
• MedDM:LLM-executable clinical guidance tree for clinical decision-making
• Rethinking Comprehensive Benchmark for Chart Understanding: A Perspective from Scientific Literature
• A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents
• In-Context Learning User Simulators for Task-Oriented Dialog Systems
• GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks
• First Multi-Dimensional Evaluation of Flowchart Comprehension for Multimodal Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems