Quanta Magazine Re-Examines LRM Reasoning: 30%–60% of Chain-of-Thought Steps Have Near-Zero Causal Impact on Answers

When OpenAI's general-purpose reasoning model settled the long-standing unit distance problem in May 2026, the question "Can AI really reason?" seemed settled. But Quanta Magazine's July 31 feature, Is AI Reasoning Right for the Wrong Reasons?, takes that optimism apart. Its conclusion is blunt: a large reasoning model's (LRM's) "chain of thought" is most likely the model muttering to itself, not a faithful record of its internal computation. Original article

1. The headline data: 30%–60% of steps can be removed with almost no change

The piece cites a 2025 paper from Northeastern University and UC Berkeley that ran causal analysis on the "thinking steps" of frontier open-source LRMs on math benchmarks. Their finding: 30%–60% of the thinking steps had "minimal causal impact" on the final answer. Chop them out, and a model's math score barely budges.

Co-author Weiyan Shi told Quanta: "We want to be careful when we review these chain-of-thought prompts because they may not be linked to the final output."

2. What the three leading voices think

The story is structured around three academic authorities:

  • Melanie Mitchell (Santa Fe Institute) supplies the most-cited three-sentence summary: "Number one: it works, it improves things. Number two: the actual text that's generated isn't necessarily faithful to what's going on inside the model. Number three: a lot of that text isn't even useful. You can actually take it out."
  • Subbarao Kambhampati (Arizona State University, former AAAI president) and his lab showed in 2025 that fully replacing a model's "correct" traces with incorrect or irrelevant ones does not degrade performance on a formal reasoning task. Even when trained only on correct traces, a model still occasionally generates invalid records of its reasoning. His 2026 ICML position paper has an unambiguous title: "Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!"
  • William Merrill (Toyota Technological Institute at Chicago), co-author of the 2024 NYU paper showing that "meaningless filler tokens" — literal strings of dots — can function in place of a human-readable chain of thought, goes further: "There's no guarantee the chain of thought has to be meaningful in any sense."

3. The mechanism: the chain of thought fills the context window, not the steps

Kambhampati's working hypothesis is that an LRM is still fundamentally an LLM, just trained to a more specific objective. The "thinking tokens" are not there to lay out a true step-by-step proof. Their job is to load up the model's context window with enough "reasoning-shaped" text so that it is more likely to probabilistically retrieve an answer that looks like reasoning. It is like muttering to yourself to jog your memory: the specific words barely matter, as long as they shake something useful loose. Pavel Izmailov (NYU, also on Anthropic's original reasoning-model team) adds that RL training may not even incentivize faithful chains: "I would say the chances are not very high."

This framing is consistent with LRM successes in "verifiable domains" such as IMO gold medals and ARC-AGI: code runs or it does not; a proof is correct or not. Those binary signals are convenient training rewards. The model does not have to learn a general reasoning process — it just has to absorb enough examples of what the steps look like, then mimic them in order to "stitch together" a plausible result that can be checked.

4. The counter-argument

OpenAI's Sébastien Bubeck pushes back: the 2025 Apple "Illusion of Thinking" findings were an artifact of outdated training tricks. "Modern models starting with GPT-5.5 do not suffer from this issue." The piece also concedes that every interviewed researcher notes the negative findings on smaller open-source LRMs may not generalize to the latest closed-source products, whose internals remain trade secrets.

5. Commentary: stop treating "thinking" as auditable evidence

Mitchell's framing is the one the whole field should sit with: "You want the right answer for the right reason, so you can trust these things." That is the real standard against which LRMs should be judged — not "does it work," but "is the process it shows me something I can stand behind."

For engineering teams this means:

  • Do not treat the LRM chain of thought as an audit log. It is unlikely to faithfully explain the answer.
  • Verifiable-domain wins (math, code) do not generalize to open-ended reasoning. "Code runs" is not the same as "general reasoning is trustworthy."
  • Interpretability research deserves more investment. We can accept black boxes à la AlphaFold when the results are independently verifiable, but for LRMs to enter high-stakes domains — scientific research, medicine, law — "right answer for the right reason" must become the bar.

Sources: Quanta Magazine feature, Northeastern & UC Berkeley arXiv paper, Kambhampati position paper, NYU filler-tokens paper by Merrill et al..