“And reasoning is still one of the core issues.”
Our reading, the sentence that was checked:
As of February 2026, reasoning is still one of the core unsolved problems for LLMs.
Assessment: Supported Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, BREAKING: LLM “reasoning” continues to be deeply flawed, paragraph 6.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-breaking-llm-reasoning-continues-4f61c1-a2
We recorded 4 claims from this post. See every claim from this post.
The wording above is the version this site observed on 2026-10-28. The source may have been edited after 2026-02-10. This page does not claim the wording was captured then.
What the claim commits to
- Kind
- Observation
- Deadline, as the speaker wrote it
- None stated. This site does not add one.
- Deadline state when assessed
- No horizon
- Deadline state on 2026-10-29
- No horizon (the release’s reference date)
From the speaker
- reasoning is still
- one of the core issues
Our interpretation
- Plain reading: as of February 2026, reasoning failures remained a major, widely recognised limitation of LLMs, not a solved problem.
Counts as supported if: Research reviews or benchmark organisations from late 2025 to early 2026 identify reasoning failures or gaps as a major remaining limitation of LLMs.
Counts as contradicted if: Authoritative evaluations in this period show that reasoning had become a solved or minor issue for frontier LLMs.
Retrospective: these criteria were written after the outcome was public.
Current assessment
Was it true for the period described?
Outcome: Supported
The dated evidence matches what the claim committed to, under the criteria frozen before grading.
Scored on a plain reading. The speaker named no measure for this claim, so it was judged on the reading an informed reader would take, stated below under our interpretation. Both reviews had to find that reading fair.
- Evidence as of
- Deadline state when assessed
- No horizon
- Assessment recorded
- Policy version
- 2026-10-28.7
Rationale
A survey by Song, Han and Goodman, submitted to arXiv on 5 February 2026, says LLMs have shown remarkable reasoning capabilities. It also says that 'significant reasoning failures persist,' even in seemingly simple scenarios (e1). On 5 December 2025 the ARC Prize Foundation said AI reasoning systems 'still exhibit many flaws' and that new ideas are still needed (e2). The same ARC Prize analysis cites 2025 progress, including ARC-AGI-2 scores, IMO gold in math and a 100% ICPC result in coding (e3). That progress does not show reasoning had become solved or minor, so it does not meet the contradiction condition. Both sources describe reasoning failures as a major remaining limitation, which fits the plain reading of 'one of the core issues.'
Limitations
- 'Core issue' is qualitative; no metric ranks reasoning failures against other limitations.
- Both sources are expert judgments, not a single measured threshold.
- The evidence records substantial reasoning progress in 2025; the claim is qualitative and does not deny that progress.
Evidence (3 items)
Supports the claim: arXiv (Song, Han, Goodman),
Despite these advances, significant reasoning failures persist, occurring even in seemingly simple scenarios.
Why it matters here: A comprehensive survey from February 2026 concludes that significant reasoning failures persist in LLMs.
- Where
- Abstract
- Publisher
- arXiv (Song, Han, Goodman)
- Kind of source
- Preprint, not peer reviewed
- Describes events of
- Public from
Supports the claim: ARC Prize Foundation,
As good as AI reasoning systems are, they still exhibit many flaws and inefficiencies necessary for AGI. We still need new ideas, like how to separate knowledge and reasoning, among others.
Why it matters here: A leading reasoning benchmark organisation said in December 2025 that reasoning systems still have many flaws and need new ideas.
- Publisher
- ARC Prize Foundation
- Kind of source
- Benchmark result
- Describes events of
- Public from
Context only: ARC Prize Foundation,
including scores from ARC-AGI-2 (static abstract reasoning), 2025 IMO Gold (math), and 2025 ICPC 100% (coding) - all being progressed by AI reasoning systems.
Why it matters here: Shows major reasoning progress in 2025. This tempers the claim but does not show that reasoning was solved.
- Publisher
- ARC Prize Foundation
- Kind of source
- Benchmark result
- Describes events of
- Public from
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, BREAKING: LLM “reasoning” continues to be deeply flawed
And reasoning is still one of the core issues.
- Where
- paragraph 6
- Published
- 2026-02-10
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-breaking-llm-reasoning-continues-4f61c1-a2: Current. Outcome: Supported. Evidence as of 2026-10-28. Public date not recorded.
Recorded events
Assessment publishedBy this site
First assessment published after both reviews and the final-text check passed.
About assessment marcus-breaking-llm-reasoning-continues-4f61c1-a2.