SYNTHESIS NOTE
TopicsFlawsthis note

Does RLVR success on math benchmarks reflect genuine reasoning improvement?

Explores whether RLVR's apparent effectiveness with spurious rewards on contaminated benchmarks like MATH-500 represents actual reasoning gains or merely data memorization retrieval.

Synthesis note · 2026-02-23 · sourced from Flaws
What does reward learning actually do to model reasoning?

The apparent success of RLVR with random, incorrect, or spurious reward signals on Qwen models may be an artifact of data contamination rather than evidence of genuine reasoning improvement.

The contamination evidence: prompting Qwen2.5-Math-7B with the first 60% of each MATH-500 question yields 54.6% exact-match reconstruction of the remaining 40% and 53.6% correct answers to these incomplete problems. On LiveMathBench — a benchmark released after Qwen2.5 — completion rate drops to 0.0%, consistent with Llama3.1-8B (3.8%/0.0% respectively). The model has memorized MATH-500.

On a fully clean benchmark (RandomCalculation — synthetic arithmetic expressions generated after Qwen's release): correct rewards deliver consistent gains surpassing the model's performance ceiling; random rewards make training highly unstable with no reliable improvement; inverse rewards rapidly erode mathematical reasoning ability.

This directly challenges Why do random rewards improve reasoning for some models but not others?. The prior interpretation — that any optimization pressure activates pretraining strategies — may confound two effects: genuine strategy activation (possible) and recall of memorized answers triggered by format-similar optimization (likely for contaminated benchmarks). On clean data, the "any reward works" finding evaporates for random and inverse signals.

The practical implication: RLVR research conclusions drawn from MATH-500 and similar benchmarks for Qwen models should be interpreted with caution. Reward engineering may matter more than the spurious-reward literature suggests — we were measuring memorization recovery, not reasoning improvement.

Inquiring lines that read this note 48

This note is a source for these research framings, grouped by the broader line of inquiry each explores. Scan the bold lines of inquiry; follow any specific question forward.

How does memorization interact with learning and generalization? Why do benchmark improvements fail to reflect actual reasoning quality? Can language model hallucination be prevented or only managed? Can ensemble evaluation methods reduce bias more than single judges? How can identical external performance mask different internal representations? How can process reward models supervise complex reasoning traces? What properties determine whether reward signals teach genuine reasoning? What constrains reinforcement learning's ability to expand model reasoning? How do training data properties shape reasoning capability development? How do we evaluate AI systems when user perception misleads actual performance? Can model confidence signals reliably improve reasoning quality and calibration? Does reinforcement learning teach reasoning or just when to reason? Can inference-time compute substitute for scaling up model parameters? Can single-axis benchmarks accurately predict agent deployment success? Do base models contain latent reasoning that training can unlock? How can AI systems learn from failures without cascading errors?

Related concepts in this collection 4

This note in its neighbourhood — explore the map, then jump to a related concept in the list below.

Concept map
13 direct connections · 106 in 2-hop network ·medium cluster Open in graph ↗

Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph

your link semantically near linked from elsewhere

Related papers in this collection 8

Papers most semantically related to this note, ranked by cosine similarity in the embedding space.

Original note title

RLVR effectiveness on contaminated benchmarks is primarily data memorization — clean benchmarks eliminate spurious reward gains