KnotBench benchmark shows state-of-the-art VLMs perform near random on diagrammatic knot reasoning tasks and lack ability to simulate structural moves.
hub
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
abstract
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. These models employ extended chain-of-thought (CoT) processes, exploring multiple strategies to enhance problem-solving capabilities. However, a critical question remains: How to intelligently and efficiently scale computational resources during testing. This paper presents the first comprehensive study on the prevalent issue of overthinking in these models, where excessive computational resources are allocated for simple problems with minimal benefit. We introduce novel efficiency metrics from both outcome and process perspectives to evaluate the rational use of computational resources by o1-like models. Using a self-training paradigm, we propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy. Experimental results show that our approach successfully reduces computational overhead while preserving model performance across a range of testsets with varying difficulty levels, such as GSM8K, MATH500, GPQA, and AIME.
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
LEAD uses online adaptive mechanisms including Potential-Scaled Instability and symmetric efficiency rewards based on correct rollouts to achieve higher accuracy-efficiency scores with substantially shorter reasoning outputs than base models on math benchmarks.
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
BET reduces reasoning tokens by about 55% on average while improving performance across benchmarks by learning to short-solve easy queries, fold early on unsolvable ones, and preserve budget for hard solvable queries.
SPEX accelerates Tree-of-Thought LLM reasoning 1.2-3x via speculative path selection, dynamic budget allocation across queries, and adaptive early termination, with up to 4.1x when combined with token speculative decoding.
VPG-EA applies variational posterior guidance and efficiency-aware distillation to compress LLM reasoning chains while preserving performance.
Hint Tuning uses an instruct model as a difficulty probe to create 1K multi-level hint examples that train reasoning models to calibrate chain-of-thought length, cutting tokens by 31.5% on average across 4B-32B models without accuracy loss.
ICR creates a virtual shorter distribution from shortest correct on-policy responses to regularize RL post-training toward concise yet accurate reasoning, improving the accuracy-length Pareto frontier on math and knowledge benchmarks.
LLM accuracy on controlled procedural arithmetic drops from 61% at 5 steps to 20% at 95 steps, with failures including skipped steps, premature answers, and hallucinated operations.
PreRL applies reward-driven updates to P(y) in pre-train space, uses Negative Sample Reinforcement to prune bad reasoning paths and boost reflection, and combines with standard RL in Dual Space RL to outperform baselines on reasoning tasks.
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.
Muon optimizer with weight decay and update scaling achieves ~2x efficiency over AdamW for large LLMs, shown via the Moonlight 3B/16B MoE model trained on 5.7T tokens.
Mixed-Policy Distillation transfers concise reasoning behavior from larger to smaller LLMs by having the teacher compress student-generated trajectories, cutting token usage up to 27% while raising benchmark scores.
Non-reasoning LLMs fail the equivalence class problem while reasoning LLMs perform better but remain incomplete, with difficulty peaking at phase transition for the former and maximum diameter for the latter.
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
SHAPE improves average math reasoning accuracy by 3% while cutting token use by 30% through stage-aware hierarchical advantage and entropy-driven token redistribution.
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
citing papers explorer
-
LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
LEAD uses online adaptive mechanisms including Potential-Scaled Instability and symmetric efficiency rewards based on correct rollouts to achieve higher accuracy-efficiency scores with substantially shorter reasoning outputs than base models on math benchmarks.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX accelerates Tree-of-Thought LLM reasoning 1.2-3x via speculative path selection, dynamic budget allocation across queries, and adaptive early termination, with up to 4.1x when combined with token speculative decoding.
-
Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness
VPG-EA applies variational posterior guidance and efficiency-aware distillation to compress LLM reasoning chains while preserving performance.
-
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
PreRL applies reward-driven updates to P(y) in pre-train space, uses Negative Sample Reinforcement to prune bad reasoning paths and boost reflection, and combines with standard RL in Dual Space RL to outperform baselines on reasoning tasks.
-
Muon is Scalable for LLM Training
Muon optimizer with weight decay and update scaling achieves ~2x efficiency over AdamW for large LLMs, shown via the Moonlight 3B/16B MoE model trained on 5.7T tokens.
-
SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning
SHAPE improves average math reasoning accuracy by 3% while cutting token use by 30% through stage-aware hierarchical advantage and entropy-driven token redistribution.
- RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference