ARXIV:2605.21299 · LLM REASONING · SUBMITTED 21 MAY · 20:34 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Tracing the ongoing emergence of human-like reasoning in Large Language Models

Paolo Morosi · Nikoleta Pantelidou · Fritz Günther · Elena Pagliarini · Evelina Leivada · arXiv

This study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments.

Blocked on Code›Score3.0Evidence unverified

Opportunity summary

Pain This study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments.

Evidence 0 refs | 3 sources | 50% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

This study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments. Large Language Models - LLMs - show human-like performance on many tasks, yet…

METHOD

Humans effortlessly go beyond literal meanings: If you mow the lawn, I will give you fifty dollars, is typically understood as implying that the speaker will pay only if the lawn is mowed, whereas…

Full abstract

Humans effortlessly go beyond literal meanings: If you mow the lawn, I will give you fifty dollars, is typically understood as implying that the speaker will pay only if the lawn is mowed, whereas If you are hungry, there is pizza in the oven implies that pizza is available regardless of the hearers hunger. Large Language Models - LLMs - show human-like performance on many tasks, yet it remains unclear whether they reason like humans. To address this, we conducted a population-matching experiment assessing how twentyfive LLMs compute conditional inferences across four languages, compared to an equal number of humans per language. We find that humans enrich logical reasoning through pragmatic inferences across languages. Model behavior is more variable. Some LLMs perfectly follow the truth-table of conditionals but they ignore pragmatic inferences, while others deviate from the truth-table, adhering to a single interpretation across the board, thus reflecting accurate rule-based processing but not human-like reasoning. Overall, LLMs are accurate semantic operators, but fail to capture the pragmatic enrichments characteristic of human reasoning. Crucially, LLM accuracy is neither predicted nor boosted by open vs. closed status, training orientation, or architecture type, suggesting that pragmatic reasoning is still an emerging ability in the cognitive toolkit of artificial systems.

RESULT

ScienceToStartup currently rates this 3.0/10 on the public viability pass. Large Language Models - LLMs - show human-like performance on many tasks, yet it remains unclear whether they reason like humans.

WHY NOW

LLM Reasoning moved forward this cycle; last verified May 2026. Public score 3.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score3.0

PainThis study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments.

Evidence0 refs | 3 sources | 50% coverage

Blockerno shell-level blocker reported

Analysis summary

This study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Competitive landscape

This study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments.

Segment

LLM Reasoning

Adoption evidence

No public code link in the paper record yet

Commercial read

3.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "d91c5ff2-af94-4056-9ef5-6616f6a24d26", "arxiv_id": "2605.21299", "canonical_route": "/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models", "endpoints": { "paper_pack": "/api/v1/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models/paper-pack", "build_passport": "/api/v1/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "Tracing the ongoing emergence of human-like reasoning in Large Language Models", "normalized_query": "2605.21299", "route": "/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models", "paper_ref": "tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models#webpage", "url": "https://sciencetostartup.com/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models", "name": "Tracing the ongoing emergence of human-like reasoning in Large Language Models", "description": "This study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models#scholarlyArticle", "headline": "Tracing the ongoing emergence of human-like reasoning in Large Language Models", "description": "This study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments.", "url": "https://sciencetostartup.com/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models", "sameAs": "https://arxiv.org/abs/2605.21299", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2605.21299" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-05-20T15:28:52.000Z", "author": [ { "@type": "Person", "name": "Paolo Morosi" }, { "@type": "Person", "name": "Nikoleta Pantelidou" }, { "@type": "Person", "name": "Fritz Günther" }, { "@type": "Person", "name": "Elena Pagliarini" }, { "@type": "Person", "name": "Evelina Leivada" } ], "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 3 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "LLM Reasoning" } ] }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "LLM Reasoning", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "Tracing the ongoing emergence of human-like reasoning in Lar", "item": "https://sciencetostartup.com/paper/tracing-the-ongoing-emergence-of-human-like-reasoning-in-large-language-models" } ] } ] }

Competitive landscape

This study compares LLM conditional inference to human pragmatic reasoning, finding LLMs are accurate semantic operators but lack human-like pragmatic enrichments.

Segment

LLM Reasoning

Adoption evidence

No public code link in the paper record yet

Commercial read

3.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Tracing the ongoing emergence of human-like reasoning in Large Language Models

Tracing the ongoing emergence of human-like reasoning in Large Language Models

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline