LLMs and humans diverge in problem-solving strategies, research finds · 7 sources tracked
ByPulseAugur Editorial·[15 sources]·
New research indicates that while both humans and large language models (LLMs) adjust their problem-solving time based on difficulty, their internal mechanisms differ significantly. Humans tend to disengage from problems they find difficult or are likely to get wrong, whereas LLMs spend more computational resources on harder problems, often leading to errors. This divergence in 'deliberation allocation' suggests LLMs' extended processing on difficult tasks stems from uncertainty rather than strategic engagement, unlike human behavior.
AI
IMPACT
Highlights a key difference in how LLMs and humans approach complex problems, suggesting current LLM reasoning strategies may not fully align with human-like flexibility.
RANK_REASON
Multiple arXiv papers discussing LLM reasoning capabilities and limitations.
arXiv:2606.28186v1 Announce Type: cross Abstract: Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Existing methods often depend on costly human calibration or item-level textual repr…
Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Existing methods often depend on costly human calibration or item-level textual representations, providing limited evidence about the …
arXiv cs.CL
TIER_1English(EN)·Bella Fascendini, Kathryn McGregor, Max D. Gupta, Thomas L. Griffiths·
arXiv:2606.27103v1 Announce Type: new Abstract: Humans flexibly adapt their reasoning strategies to the requirements of a given problem. Large language models (LLMs) have performed well on many cognitive tasks, however, it is unclear whether this accuracy is a result of pattern m…
arXiv:2606.26108v1 Announce Type: new Abstract: Larger language models consistently outperform smaller ones on reasoning benchmarks, yet the reasoning differences underlying this gap remain underexplored. Across benchmarks in mathematics, physics, chemistry, and programming, we o…
arXiv:2601.03388v3 Announce Type: replace-cross Abstract: Earlier research has shown that metaphors influence human decision-making, raising the question of whether metaphors also influence large language models (LLMs)' reasoning pathways, given that their training data contain a…
arXiv cs.LG
TIER_1English(EN)·Hongyi Henry Jin, Wenhan Yang, Meysam Ghaffari, Carlos Morato, Baharan Mirzasoleiman·
arXiv:2606.26797v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities in Large Language Models (LLMs). However, existing methods for curating high-qua…
arXiv:2606.26502v1 Announce Type: new Abstract: Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items. When an LRM gets a problem wrong, it spends more tokens than when it gets the same prob…
Humans flexibly adapt their reasoning strategies to the requirements of a given problem. Large language models (LLMs) have performed well on many cognitive tasks, however, it is unclear whether this accuracy is a result of pattern matching from training data or flexible reasoning…
Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities in Large Language Models (LLMs). However, existing methods for curating high-quality SFT data rely heavily on strong reasoning m…
arXiv cs.CL
TIER_1English(EN)·Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Kevin El Haddad, C\'eline Hudelot, Pierre Colombo·
arXiv:2509.22193v2 Announce Type: replace Abstract: Distilling reasoning traces from strong teacher models has become the standard recipe for building capable small language models. Yet reasoning traces are 5-20$\times$ longer than standard instruction fine-tuning (IFT) outputs, …
Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items. When an LRM gets a problem wrong, it spends more tokens than when it gets the same problem right; humans do the reverse, spending less …
Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items. When an LRM gets a problem wrong, it spends more tokens than when it gets the same problem right; humans do the reverse, spending less …
dev.to — LLM tag
TIER_1English(EN)·Dhruv Aggarwal·
<p>Imagine you are asked to solve a complex math problem. If you answer immediately, you’ll likely rely on intuition or a guess. But if you are given ten minutes to scratch out ideas, double-check your logic, and correct your mistakes before speaking, your accuracy improves signi…
When should a reasoning model quit a problem it probably can't solve? Conformal Thinking sets stop/continue thresholds for test-time compute by distribution-free risk control, holding the error rate under a target you pick. It adds a lower threshold that gives up early when confi…
