{"total":15,"rows":[{"id":"2508.10751","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","created":"2025-08-14","cited_by_count":138,"area":"lr"},{"id":"2510.12164","title":"A Survey on Parallel Reasoning","created":"2025-10-14","cited_by_count":11,"area":"lr"},{"id":"2507.06829","title":"Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework","created":"2025-07-09","cited_by_count":10,"area":"lr"},{"id":"2511.04341","title":"Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning","created":"2025-11-06","cited_by_count":4,"area":"lr"},{"id":"2510.16374","title":"Before you <think>, monitor: Implementing Flavell's metacognitive framework in LLMs","created":"2025-10-18","cited_by_count":3,"area":"lr"},{"id":"2509.05007","title":"Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework","created":"2025-09-05","cited_by_count":2,"area":"lr"},{"id":"2605.27030","title":"Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2509.22044","title":"A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2601.11940","title":"Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart","created":"2026-01-17","cited_by_count":1,"area":"lr"},{"id":"2602.00759","title":"Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning","created":"2026-01-31","cited_by_count":1,"area":"lr"},{"id":"2604.13356","title":"Peer-Predictive Self-Training for Language Model Reasoning","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2605.10344","title":"TMAS: Scaling Test-Time Compute via Multi-Agent Synergy","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2509.23730","title":"EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance","created":"2025-09-28","cited_by_count":0,"area":"lr"},{"id":"2602.08344","title":"OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2604.16029","title":"Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning","created":"2026-04-17","cited_by_count":0,"area":"lr"}],"next_cursor":null}