REVIEW 11 cited by
Think Only When You Need with Large Hybrid-Reasoning Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Think Only When You Need with Large Hybrid-Reasoning Models
read the original abstract
Recent Large Reasoning Models (LRMs) have shown substantially improved reasoning capabilities over traditional Large Language Models (LLMs) by incorporating extended thinking processes prior to producing final responses. However, excessively lengthy thinking introduces substantial overhead in terms of token consumption and latency, which is particularly unnecessary for simple queries. In this work, we introduce Large Hybrid-Reasoning Models (LHRMs), the first kind of model capable of adaptively determining whether to perform thinking based on the contextual information of user queries. To achieve this, we propose a two-stage training pipeline comprising Hybrid Fine-Tuning (HFT) as a cold start, followed by online reinforcement learning with the proposed Hybrid Group Policy Optimization (HGPO) to implicitly learn to select the appropriate thinking mode. Furthermore, we introduce a metric called Hybrid Accuracy to quantitatively assess the model's capability for hybrid thinking. Extensive experimental results show that LHRMs can adaptively perform hybrid thinking on queries of varying difficulty and type. It outperforms existing LRMs and LLMs in reasoning and general capabilities while significantly improving efficiency. Together, our work advocates for a reconsideration of the appropriate use of extended thinking processes and provides a solid starting point for building hybrid thinking systems.
Forward citations
Cited by 11 Pith papers
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning
TIME trains LLMs to trigger compact, context-triggered reasoning via time tags and tick events, improving TIMEBench scores while cutting explicit reasoning tokens by an order of magnitude.
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
-
HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
HiRO-Nav adaptively triggers reasoning only on high-entropy actions via a hybrid training pipeline and shows better success-token trade-offs than always-reason or never-reason baselines on the CHORES-S benchmark.
-
ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure
Multi-question prompts elicit shorter chain-of-thought traces, and fine-tuning on those traces transfers the compression to single-question reasoning.
-
AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification
An entropy-guided reward that shortens answers to easy, confident questions and extends reasoning on hard ones reduces medical QA tokens by 4.7x to 6.4x with minimal accuracy loss.
-
Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
EviOmni unifies evidence reasoning and extraction in a single RL trajectory with token masking and verifiable rewards for answer, length, and format to produce compact high-quality evidence for RAG.
-
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
MUR dynamically allocates LLM reasoning budgets by aggregating stepwise uncertainty with momentum, cutting tokens over 45% while raising accuracy 0.33-3.46% on MATH-500, AIME, and GPQA.
-
Efficient Reasoning on the Edge
LoRA adapters, budget-forced GRPO, dynamic switching, parallel verification and FPTQuant enable practical chain-of-thought reasoning on quantized Qwen2.5-7B for edge devices.
-
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
Early entropy dynamics during LLM decoding mark when explicit reasoning becomes beneficial, enabling the training-free EDRM router that selects strategies per instance and yields 41-55% token savings with accuracy gai...
-
Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
A survey that maps reinforcement learning methods, datasets, benchmarks, and open-source tools across the full training lifecycle of large language models, focusing on verifiable-reward reasoning.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.