{"total":16,"rows":[{"id":"2504.05419","title":"Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification","created":"2025-04-07","cited_by_count":159,"area":"lr"},{"id":"2504.15279","title":"VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models","created":"2025-04-21","cited_by_count":107,"area":"lr"},{"id":"2405.13144","title":"LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages","created":"2024-05-21","cited_by_count":49,"area":"lr"},{"id":"2402.11291","title":"Puzzle Solving using Reasoning of Large Language Models: A Survey","created":"2024-02-17","cited_by_count":45,"area":"lr"},{"id":"2506.04810","title":"Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study","created":"2025-06-05","cited_by_count":17,"area":"lr"},{"id":"2406.13764","title":"Can LLMs Reason in the Wild with Programs?","created":"2024-06-19","cited_by_count":13,"area":"lr"},{"id":"2411.02570","title":"TI-PREGO: Chain of Thought and In-Context Learning for Online Mistake Detection in PRocedural EGOcentric Videos","created":"2024-11-04","cited_by_count":10,"area":"lr"},{"id":"2406.00284","title":"A Closer Look at Logical Reasoning with LLMs: The Choice of Tool Matters","created":"2024-06-01","cited_by_count":8,"area":"lr"},{"id":"2402.11903","title":"DiLA: Enhancing LLM Tool Learning with Differential Logic Layer","created":"2024-02-19","cited_by_count":6,"area":"lr"},{"id":"2408.16081","title":"Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents","created":"2024-08-28","cited_by_count":5,"area":"lr"},{"id":"2502.12275","title":"Integrating Expert Knowledge into Logical Programs via LLMs","created":"2025-02-17","cited_by_count":3,"area":"lr"},{"id":"2410.12298","title":"Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphs","created":"2024-10-16","cited_by_count":2,"area":"lr"},{"id":"2509.01619","title":"Throttling Web Agents Using Reasoning Gates","created":"2025-09-01","cited_by_count":2,"area":"lr"},{"id":"2505.11141","title":"Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2507.19749","title":"Can LLMs Solve ASP Problems? Insights from a Benchmarking Study (Extended Version)","created":"2025-07-26","cited_by_count":1,"area":"lr"},{"id":"2605.06444","title":"SCRuB: Social Concept Reasoning under Rubric-Based Evaluation","created":"2026-05-07","cited_by_count":1,"area":"lr"}],"next_cursor":null}