REVIEW 17 cited by
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
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
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
read the original abstract
Large language models (LLMs) such as OpenAI's o1 have demonstrated remarkable abilities in complex reasoning tasks by scaling test-time compute and exhibiting human-like deep thinking. However, we identify a phenomenon we term underthinking, where o1-like LLMs frequently switch between different reasoning thoughts without sufficiently exploring promising paths to reach a correct solution. This behavior leads to inadequate depth of reasoning and decreased performance, particularly on challenging mathematical problems. To systematically analyze this issue, we conduct experiments on three challenging test sets and two representative open-source o1-like models, revealing that frequent thought switching correlates with incorrect responses. We introduce a novel metric to quantify underthinking by measuring token efficiency in incorrect answers. To address underthinking, we propose a decoding strategy with thought switching penalty TIP that discourages premature transitions between thoughts, encouraging deeper exploration of each reasoning path. Experimental results demonstrate that our approach improves accuracy across challenging datasets without requiring model fine-tuning. Our findings contribute to understanding reasoning inefficiencies in o1-like LLMs and offer a practical solution to enhance their problem-solving capabilities.
Forward citations
Cited by 17 Pith papers
-
Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning
Hilbert-Geo creates the first unified formal language for solid geometry and a two-step parsing-then-reasoning method that reaches SOTA accuracy on solid geometry benchmarks.
-
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
DASH assigns segment-level credit in reasoning traces using drift toward ground-truth answers, yielding 50.8% accuracy on AIME25 versus 45.4% for GRPO while reducing overthinking behaviors.
-
Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
MentalMap benchmark identifies a universal L3 reasoning cliff in LLMs' text-based spatial reasoning that persists across languages, scales, and prompting, and is replicated in human evaluations.
-
Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning
Hilbert-Geo introduces a unified formal language framework with CDL predicates and theorem bank for solid geometry, using a Parse2Reason pipeline to achieve SOTA accuracy on new solid and plane geometry datasets.
-
L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
LCPO trains L1 reasoning models to adhere to prompt-specified CoT lengths, supporting accuracy-compute trade-offs and yielding short reasoning models that outperform larger baselines at matched lengths.
-
CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning
A monitoring-guided rollback controller produced a small and statistically uncertain accuracy gain on first-seen MATH-500 problems, and a larger exploratory gain on a historical-coverage set contaminated by manual thr...
-
Addressing Over-Refusal in LLMs with Competing Rewards
SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.
-
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
-
STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes
STOP uses structured on-policy analysis to prune long reasoning traces to their earliest correct node, cutting token usage 19-42% with little accuracy loss on math benchmarks.
-
CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems
CAM ranks how much each intermediate output of a multi-agent code-generation system causally matters for final correctness, then uses that ranking to repair failures and prune features.
-
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
SAE-Steering finds, via keyword-logit recall plus effectiveness ranking, sparse-autoencoder features that steer a reasoning model into a chosen reasoning strategy, beating baseline steering by ~15% on a judge-based me...
-
CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models
CAT uses intrinsic confidence signals in preference optimization to adapt reasoning length in LRMs, outperforming uniform compression baselines on accuracy across benchmarks.
-
Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes
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.
-
SuCo: Sufficiency-guided Continuous Adaptive Reasoning
SuCo defines minimal sufficient CoT and applies a two-stage fine-tuning plus RL framework to enable continuous adaptive reasoning control, claiming gains in both accuracy and token efficiency on math, code, and science tasks.
-
The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.
-
OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
A new open SFT dataset for reasoning distillation lets coding models hit state-of-the-art scores on LiveCodeBench and CodeContests with supervised fine-tuning alone, outperforming RL-trained baselines.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.