{"total":18,"rows":[{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2608.04001","title":"Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2510.19028","title":"Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues","created":"2025-10-21","cited_by_count":3,"area":"lr"},{"id":"2512.24572","title":"Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs' Legal Reasoning Capabilities","created":"2025-12-31","cited_by_count":3,"area":"lr"},{"id":"2601.22249","title":"FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2508.12265","title":"Fast, Slow, and Tool-augmented Thinking for LLMs: A Review","created":"2025-08-17","cited_by_count":2,"area":"lr"},{"id":"2509.22230","title":"In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2509.17807","title":"Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark","created":"2025-09-22","cited_by_count":1,"area":"lr"},{"id":"2509.19893","title":"Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2510.09227","title":"RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2603.10960","title":"Ranking Reasoning LLMs under Test-Time Scaling","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2509.11303","title":"Ko-PIQA: A Korean Physical Commonsense Reasoning Dataset with Cultural Context","created":"2025-09-14","cited_by_count":0,"area":"lr"},{"id":"2510.24150","title":"Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean","created":"2025-10-28","cited_by_count":0,"area":"lr"},{"id":"2601.03286","title":"HyperCLOVA X 32B Think","created":"2026-01-03","cited_by_count":0,"area":"lr"},{"id":"2604.24645","title":"K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology","created":"2026-04-27","cited_by_count":0,"area":"lr"},{"id":"2610.07803","title":"ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.17767","title":"Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.18862","title":"DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}