{"total":17,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2205.14268","title":"NeuPSL: Neural Probabilistic Soft Logic","created":"2022-05-27","cited_by_count":34,"area":"lr"},{"id":"2210.12040","title":"Neuro-Symbolic Causal Reasoning Meets Signaling Game for Emergent Semantic Communications","created":"2022-10-21","cited_by_count":21,"area":"lr"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2410.20957","title":"Neuro-symbolic Learning Yielding Logical Constraints","created":"2024-10-28","cited_by_count":12,"area":"lr"},{"id":"2604.14853","title":"Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization","created":"2026-04-16","cited_by_count":9,"area":"lr"},{"id":"2503.06518","title":"Towards Superior Quantization Accuracy: A Layer-sensitive Approach","created":"2025-03-09","cited_by_count":8,"area":"lr"},{"id":"2602.04620","title":"QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2604.21510","title":"OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving","created":"2026-04-23","cited_by_count":3,"area":"lr"},{"id":"2608.08176","title":"Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation","created":"2026-08-08","cited_by_count":3,"area":"lr"},{"id":"2604.04929","title":"Rethinking Model Efficiency: Multi-Agent Inference with Large Models","created":"2026-04-06","cited_by_count":2,"area":"lr"},{"id":"2606.03092","title":"The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2310.09383","title":"Integrating Symbolic Reasoning into Neural Generative Models for Design Generation","created":"2023-10-13","cited_by_count":1,"area":"lr"},{"id":"2603.09221","title":"Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2601.10274","title":"Queueing-Aware Optimization of Reasoning Tokens for Accuracy-Latency Trade-offs in LLM Servers","created":"2026-01-15","cited_by_count":0,"area":"lr"},{"id":"2605.04243","title":"Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2610.00332","title":"The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}