Contact and support
Need help, have a question, or want to contact the ResearchHub team?
© 2026 ResearchHub. Built for responsible scholarly connection.
Privacy-aware community infrastructureResearch graph
References from Efficient Inference for Large Reasoning Models: A Survey. Local targets link to admitted publications; unresolved targets remain external evidence.
Introducing ChatGPT
2022 · External reference
American invitational mathematics examination
2025 · External reference
Introducing deep research
2025 · External reference
OpenAI o1 system card
2024 · External reference
OpenAI o3-mini system card
2025 · External reference
10.1038/s41586-025-09422-z
10.1038/s41586-025-09422-z · External reference
Kimi k1. 5: Scaling reinforcement learning with LLMs
2025 · External reference
Kimi k2: Open agentic intelligence
2025 · External reference
Rethinking bottlenecks in safety fine-tuning of vision language models
2025 · External reference
Model compression and efficient inference for large language models: A survey
2024 · External reference
10.52202/085713-1689
10.52202/085713-1689 · External reference
DeepSeek-V3 technical report
2024 · External reference
A survey on efficient inference for large language models
2024 · External reference
10.18653/v1/2025.emnlp-main.1236
10.18653/v1/2025.emnlp-main.1236 · External reference
10.1016/j.ins.2026.123939
10.1016/j.ins.2026.123939 · External reference
Chain of draft: Thinking faster by writing less
2025 · External reference
10.18653/v1/2025.findings-acl.1274
10.18653/v1/2025.findings-acl.1274 · External reference
10.18653/v1/2026.findings-acl.649
10.18653/v1/2026.findings-acl.649 · External reference
Making small language models efficient reasoners: Intervention, supervision, reinforcement
2025 · External reference
Fractured chain-of-thought reasoning
2025 · External reference
10.52202/085713-4668
10.52202/085713-4668 · External reference
ThinkLess: A training-free inference-efficient method for reducing reasoning redundancy
2025 · External reference
Plan and budget: Effective and efficient test-time scaling on large language model reasoning
2025 · External reference
TRIMR: Verifier-based training-free thinking compression for efficient test-time scaling
2025 · External reference
Solar: Scalable optimization of large-scale architecture for reasoning
2025 · External reference
10.1609/aaai.v39i23.34608
10.1609/aaai.v39i23.34608 · External reference
10.18653/v1/2025.emnlp-main.165
10.18653/v1/2025.emnlp-main.165 · External reference
InftyThink: Breaking the length limits of long-context reasoning in large language models
2025 · External reference
10.18653/v1/2025.emnlp-main.673
10.18653/v1/2025.emnlp-main.673 · External reference
10.18653/v1/2025.acl-long.300
10.18653/v1/2025.acl-long.300 · External reference
Distilling system 2 into system 1
2024 · External reference
10.18653/v1/2025.findings-acl.1289
10.18653/v1/2025.findings-acl.1289 · External reference
10.52202/079017-1441
10.52202/079017-1441 · External reference
10.18653/v1/2025.emnlp-industry.160
10.18653/v1/2025.emnlp-industry.160 · External reference
10.18653/v1/2026.findings-acl.697
10.18653/v1/2026.findings-acl.697 · External reference
Optimizing test-time compute via meta reinforcement fine-tuning
2025 · External reference
10.52202/085713-2032
10.52202/085713-2032 · External reference
Claude 3.7 Sonnet and Claude code
2025 · External reference
L1: Controlling how long a reasoning model thinks with reinforcement learning
2025 · External reference
10.18653/v1/2025.findings-acl.956
10.18653/v1/2025.findings-acl.956 · External reference
Think smarter not harder: Adaptive reasoning with inference aware optimization
2025 · External reference
Long-short chain-of-thought mixture supervised fine-tuning eliciting efficient reasoning in large language models
2025 · External reference
10.18653/v1/2025.emnlp-main.405
10.18653/v1/2025.emnlp-main.405 · External reference
Scalable chain of thoughts via elastic reasoning
2025 · External reference
10.52202/085713-1608
10.52202/085713-1608 · External reference
Accelerating chain-of-thought reasoning: When goal-gradient importance meets dynamic skipping
External reference
10.52202/085713-5760
10.52202/085713-5760 · External reference
10.52202/068431-1800
10.52202/068431-1800 · External reference
10.52202/085713-3775
10.52202/085713-3775 · External reference
VAPO: Efficient and reliable reinforcement learning for advanced reasoning tasks
2025 · External reference
SimpleRL-Zoo: Investigating and taming zero reinforcement learning for open base models in the wild
2025 · External reference
Efficient reinforcement finetuning via adaptive curriculum learning
2025 · External reference
10.1007/s11432-025-4665-8
10.1007/s11432-025-4665-8 · External reference
10.18653/v1/2025.emnlp-main.1025
10.18653/v1/2025.emnlp-main.1025 · External reference
10.52202/085713-4815
10.52202/085713-4815 · External reference
Inference scaling laws: An empirical analysis of compute-optimal inference for LLM problem-solving
2024 · External reference
Scaling LLM test-time compute optimally can be more effective than scaling parameters for reasoning
2024 · External reference
Think deep, think fast: Investigating efficiency of verifier-free inference-time-scaling methods
2025 · External reference
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
2025 · External reference
RedStar: Does scaling long-CoT data unlock better slow-reasoning systems
2025 · External reference
O1 replication journey–Part 3: Inference-time scaling for medical reasoning
2025 · External reference
10.1609/aaai.v39i23.34663
10.1609/aaai.v39i23.34663 · External reference
Do not think that much for 2 3=? On the overthinking of o1-like LLMs
2024 · External reference
When more is less: Understanding chain-of-thought length in LLMs
2025 · External reference
The danger of overthinking: Examining the reasoning-action dilemma in agentic tasks
2025 · External reference
Overthink: Slowdown attacks on reasoning LLMs
2025 · External reference
10.52202/085713-3403
10.52202/085713-3403 · External reference
Reasoning models can be effective without thinking
2025 · External reference
Cothink: Token-efficient reasoning via instruct models guiding reasoning models
2025 · External reference
10.18653/v1/2025.findings-emnlp.394
10.18653/v1/2025.findings-emnlp.394 · External reference
Efficient reasoning through suppression of self-affirmation reflections in large reasoning models
2025 · External reference
10.18653/v1/2025.findings-naacl.383
10.18653/v1/2025.findings-naacl.383 · External reference
10.52202/079017-1025
10.52202/079017-1025 · External reference
Reward-guided speculative decoding for efficient LLM reasoning
2025 · External reference
FlashThink: An early exit method for efficient reasoning
2025 · External reference
Large reasoning models know how to think efficiently
2025 · External reference
10.52202/085713-2623
10.52202/085713-2623 · External reference
Not all tokens are what you need in thinking
2025 · External reference
10.52202/085713-4337
10.52202/085713-4337 · External reference
10.18653/v1/2025.emnlp-main.904
10.18653/v1/2025.emnlp-main.904 · External reference
10.52202/085713-5246
10.52202/085713-5246 · External reference
Activation steering for chain-of-thought compression
2025 · External reference
Uncovering latent chain of thought vectors in large language models
2025 · External reference
SelfBudgeter: Adaptive token allocation for efficient LLM reasoning
2025 · External reference
Can pruning improve reasoning? revisiting long-CoT compression with capability in mind for better reasoning
2025 · External reference
10.52202/085713-4204
10.52202/085713-4204 · External reference
DRP: Distilled reasoning pruning with skill-aware step decomposition for efficient large reasoning models
2025 · External reference
10.18653/v1/2025.findings-emnlp.770
10.18653/v1/2025.findings-emnlp.770 · External reference
R1-compress: Long chain-of-thought compression via chunk compression and search
2025 · External reference
10.52202/085713-3594
10.52202/085713-3594 · External reference
Non-myopic generation of language models for reasoning and planning
2024 · External reference
10.52202/079017-1740
10.52202/079017-1740 · External reference
LIMO: Less is more for reasoning
2025 · External reference
10.18653/v1/2024.emnlp-main.333
10.18653/v1/2024.emnlp-main.333 · External reference
Improving mathematical reasoning capabilities of small language models via feedback-driven distillation
2024 · External reference
10.18653/v1/2025.findings-acl.1068
10.18653/v1/2025.findings-acl.1068 · External reference
SmartThinker: Learning to compress and preserve reasoning by step-level length control
2025 · External reference
PREMISE: Scalable and strategic prompt optimization for efficient mathematical reasoning in large models
2025 · External reference
Less data less tokens: Multilingual unification learning for efficient test-time reasoning in LLMs
2025 · External reference
10.18653/v1/2025.findings-emnlp.845
10.18653/v1/2025.findings-emnlp.845 · External reference
ConciseHint: Boosting efficient reasoning via continuous concise hints during generation
External reference
10.18653/v1/2026.findings-acl.1866
10.18653/v1/2026.findings-acl.1866 · External reference
10.18653/v1/2026.acl-long.1856
10.18653/v1/2026.acl-long.1856 · External reference
10.52202/085713-5629
10.52202/085713-5629 · External reference
Implicit chain of thought reasoning via knowledge distillation
2023 · External reference
10.18653/v1/2025.emnlp-main.36
10.18653/v1/2025.emnlp-main.36 · External reference
From explicit cot to implicit CoT: Learning to internalize CoT step by step
2024 · External reference
Training large language models to reason in a continuous latent space
2024 · External reference
Compressed chain of thought: Efficient reasoning through dense representations
2024 · External reference
Efficient reasoning with hidden thinking
2025 · External reference
Token assorted: Mixing latent and text tokens for improved language model reasoning
2025 · External reference
10.18653/v1/2025.acl-long.1137
10.18653/v1/2025.acl-long.1137 · External reference
10.52202/085713-0164
10.52202/085713-0164 · External reference
10.1609/aaai.v40i40.40659
10.1609/aaai.v40i40.40659 · External reference
10.18653/v1/2025.emnlp-main.256
10.18653/v1/2025.emnlp-main.256 · External reference
Rethinking LLM-based preference evaluation
2024 · External reference
10.18653/v1/2025.findings-emnlp.358
10.18653/v1/2025.findings-emnlp.358 · External reference
10.52202/085713-1302
10.52202/085713-1302 · External reference
Fast on the easy, deep on the hard: Efficient reasoning via powered length penalty
2025 · External reference
ThinkPrune: Pruning long chain-of-thought of LLMs via reinforcement learning
2025 · External reference
Do thinking tokens help or trap? Towards more efficient large reasoning model
2025 · External reference
10.18653/v1/2026.acl-long.726
10.18653/v1/2026.acl-long.726 · External reference
AdapThink: Adaptive thinking preferences for reasoning language model
2025 · External reference
Think when you need: Self-adaptive chain-of-thought learning
2025 · External reference
TINA: Tiny reasoning models via LoRA
2025 · External reference
10.52202/085713-0365
10.52202/085713-0365 · External reference
Exploring and exploiting the inherent efficiency within large reasoning models for self-guided efficiency enhancement
2025 · External reference
Efficient RL training for reasoning models via length-aware optimization
2025 · External reference
Learn to reason efficiently with adaptive length-based reward shaping
2025 · External reference
10.52202/085713-5108
10.52202/085713-5108 · External reference
10.52202/085713-0793
10.52202/085713-0793 · External reference
Overclocking LLM reasoning: Monitoring and controlling thinking path lengths in LLMs
2025 · External reference
Not all thoughts are generated equal: Efficient LLM reasoning via multi-turn reinforcement learning
2025 · External reference
10.18653/v1/2025.findings-emnlp.927
10.18653/v1/2025.findings-emnlp.927 · External reference
10.18653/v1/2025.findings-acl.1125
10.18653/v1/2025.findings-acl.1125 · External reference
Walk before you run! concise LLM reasoning via reinforcement learning
2025 · External reference
Optimizing length compression in large reasoning models
2025 · External reference
AALC: Large language model efficient reasoning via adaptive accuracy-length control
2025 · External reference
10.52202/085713-3707
10.52202/085713-3707 · External reference
Expediting and elevating large language model reasoning via hidden chain-of-thought decoding
External reference
Do LLMs really think step-by-step in implicit reasoning
2025 · External reference
Training verifiers to solve math word problems
External reference
10.18653/v1/2024.eacl-short.15
10.18653/v1/2024.eacl-short.15 · External reference
10.18653/v1/2021.naacl-main.168
10.18653/v1/2021.naacl-main.168 · External reference
10.18653/v1/p17-1015
10.18653/v1/p17-1015 · External reference
10.18653/v1/2020.acl-main.92
10.18653/v1/2020.acl-main.92 · External reference
10.18653/v1/2024.findings-acl.411
10.18653/v1/2024.findings-acl.411 · External reference
10.18653/v1/2023.emnlp-main.489
10.18653/v1/2023.emnlp-main.489 · External reference
Measuring mathematical problem solving with the math dataset
2021 · External reference
MetaMath: Bootstrap your own mathematical questions for large language models
External reference
10.18653/v1/2024.acl-long.211
10.18653/v1/2024.acl-long.211 · External reference
GPQA: A graduate-level google-proof Q&A benchmark
2024 · External reference
10.1609/aaai.v34i05.6319
10.1609/aaai.v34i05.6319 · External reference
10.63317/28283yn8kzpn
10.63317/28283yn8kzpn · External reference
LiveCodeBench: Holistic and contamination free evaluation of large language models for code
External reference
SWE-bench: Can language models resolve real-world github issues?
External reference
Language models are greedy reasoners: A systematic formal analysis of chain-of-thought
2023 · External reference
10.24963/ijcai.2020/501
10.24963/ijcai.2020/501 · External reference
ReClor: A reading comprehension dataset requiring logical reasoning
2020 · External reference
10.18653/v1/n19-1421
10.18653/v1/n19-1421 · External reference
10.18653/v1/d18-1260
10.18653/v1/d18-1260 · External reference
10.18653/v1/2021.acl-long.238
10.18653/v1/2021.acl-long.238 · External reference
10.1162/tacl_a_00370
10.1162/tacl_a_00370 · External reference
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
2022 · External reference
10.18653/v1/2023.findings-acl.824
10.18653/v1/2023.findings-acl.824 · External reference
10.18653/v1/d18-1259
10.18653/v1/d18-1259 · External reference
10.1162/tacl_a_00475
10.1162/tacl_a_00475 · External reference
Measuring massive multitask language understanding
2020 · External reference
10.1109/cvpr52733.2024.00913
10.1109/cvpr52733.2024.00913 · External reference
10.52202/068431-0182
10.52202/068431-0182 · External reference
SciBench: Evaluating college-level scientific problem-solving abilities of large language models
2024 · External reference
10.52202/079017-3014
10.52202/079017-3014 · External reference
Evaluating mathematical reasoning of foundation models in visual contexts
2024 · External reference
τ-bench: A benchmark for tool-agent-user interaction in real-world domains
External reference
10.18653/v1/d19-1259
10.18653/v1/d19-1259 · External reference
10.56726/irjmets45213
10.56726/irjmets45213 · External reference
10.1186/s13000-024-01464-7
10.1186/s13000-024-01464-7 · External reference
10.1145/3630106.3659048
10.1145/3630106.3659048 · External reference
Monitoring monitorability
2025 · External reference
Chain-of-thought reasoning in the wild is not always faithful
2025 · External reference
10.52202/085713-1654
10.52202/085713-1654 · External reference
10.1609/aaai.v40i38.40486
10.1609/aaai.v40i38.40486 · External reference
10.18653/v1/2024.acl-long.254
10.18653/v1/2024.acl-long.254 · External reference
General purpose verification for chain of thought prompting
2024 · External reference
A pragmatic way to measure chain-of-thought monitorability
2025 · External reference
FlipAttack: Jailbreak LLMs via flipping
2024 · External reference
Evaluating the paperclip maximizer: Are RL-based language models more likely to pursue instrumental goals
2025 · External reference
Privacy in large language models: Attacks, defenses and future directions
External reference
10.18653/v1/2025.findings-emnlp.185
10.18653/v1/2025.findings-emnlp.185 · External reference
10.1609/aaai.v34i05.6319
10.1609/aaai.v34i05.6319 · External reference
10.52202/085713-0977
10.52202/085713-0977 · External reference
10.52202/085713-0977
10.52202/085713-0977 · External reference
Efficient reasoning via chain of unconscious thought
2025 · External reference
10.1007/s13278-025-01428-9
10.1007/s13278-025-01428-9 · External reference
10.18653/v1/2025.emnlp-main.277
10.18653/v1/2025.emnlp-main.277 · External reference
Introducing GPT-4.5
2025 · External reference
10.1109/cvpr52734.2025.00168
10.1109/cvpr52734.2025.00168 · External reference
Gemini robotics brings AI into the physical world
2025 · External reference
Nvidia isaac GR00T N1: An open foundation model for humanoid
2025 · External reference
10.1145/3802463.3802475
10.1145/3802463.3802475 · External reference
LLM4Drive: A survey of large language models for autonomous driving
External reference
10.18653/v1/2023.findings-emnlp.936
10.18653/v1/2023.findings-emnlp.936 · External reference
Linear-time sequence modeling with selective state spaces
External reference
10.1145/3787849
10.1145/3787849 · External reference
Unlocking efficient long-to-short LLM reasoning with model merging
2025 · External reference
The Llama 3 herd of models
2024 · External reference
RouteLLM: Learning to route LLMs from preference data
2025 · External reference
Learning to route LLMs with confidence tokens
2025 · External reference
Confident or seek stronger: Exploring uncertainty-based on-device LLM routing from benchmarking to generalization
2025 · External reference
