REVIEW 11 cited by
The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer
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
The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer
read the original abstract
Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and reinforcement learning. However, many open questions remain regarding the interplay between reasoning token usage and accuracy gains. In particular, when comparing models across generations, it is unclear whether improved performance results from longer reasoning chains or more efficient reasoning. We systematically analyze reasoning chain length across o1-mini and o3-mini variants on the Omni-MATH benchmark, finding that o3-mini (m) achieves superior accuracy without requiring longer reasoning chains than o1-mini. Moreover, we show that accuracy generally declines as reasoning chains grow across all models and compute settings, even when controlling for difficulty of the questions. This accuracy drop is significantly smaller in more proficient models, suggesting that new generations of reasoning models use test-time compute more effectively. Finally, we highlight that while o3-mini (h) achieves a marginal accuracy gain over o3-mini (m), it does so by allocating substantially more reasoning tokens across all problems, even the ones that o3-mini (m) can already solve. These findings provide new insights into the relationship between model capability and reasoning length, with implications for efficiency, scaling, and evaluation methodologies.
Forward citations
Cited by 11 Pith papers
-
Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design
A single diffusion transformer trains on tokenized robot bodies and motions to generate and optimize robot designs for unseen rewards and trajectories, outpacing evolutionary search in speed and often in reward.
-
Can AI Agents Synthesize Scientific Conclusions?
A new benchmark and clean-room harness show frontier AI agents reach only 0.337 factual F1 when synthesizing conclusions from scientific evidence.
-
When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models
LLM first-answer accuracy on procedural arithmetic drops from 61% on 5-step tasks to 20% on 95-step tasks, with frequent failures including skipped steps, premature answers, and hallucinated operations.
-
When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling
A large-scale empirical study categorizes bugs in LLM agents and demonstrates that a specialized LLM agent can annotate them accurately at very low cost.
-
POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems
POIROT protocol repurposes agents in LLM multi-agent systems as an internal diagnostic layer for failure detection, outperforming single-LLM evaluators with gains that increase with complexity, agent count, and fault types.
-
When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models
A new benchmark shows LLM first-answer accuracy on procedural arithmetic drops from 63% (5 steps) to 20% (95 steps) due to execution failures like skipped steps and premature answers.
-
When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models
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.
-
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
LRMs exhibit complete accuracy collapse beyond certain puzzle complexities, with reasoning effort rising then declining, outperforming standard LLMs only on medium-complexity tasks.
-
Reason Before You Retrieve: Agentic Planning for Multi-modal RAG
MM-R2 claims SOTA multimodal RAG accuracy on InfoSeek and Encyclopedic VQA via intent grounding plus a 10-topic KnowledgeMap, but its teacher trajectories leak the gold Wikipedia page and omit the image.
-
When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models
Across 15 LLMs, first-answer accuracy on arithmetic procedural execution falls from 63% at 5 steps to 20% at 95 steps, with under-execution increasing.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.