Test-time scaling: open-access research

Journal article

Perspectives Without Independence: Multi-Agent and Multi-Persona Reasoning Under Compute-Normalised Comparison, Why the Gains That Survive Are Not the Ones Diversity Predicts, and the Controls That Would Tell Them Apart

Pranay Mahendrakar 2026

Multi-agent debate, multi-persona prompting and related schemes are usually justified by diversity of viewpoint: several perspectives err differently, so their combination is more reliable than any one of them. That justification is a claim about independent errors, and a scheme that samples all…

Cite Related research LOR-00074 · 10 views · 21 downloads

PDF537.5 KB

Journal article

A Step Score Is Not a Step Verdict: Three Quantities Under the Name Process Supervision, and the Outcome-Only Results That Make the Distinction Load-Bearing

Pranay M. Mahendrakar 2026

Process reward models are introduced, almost without exception, as models that score whether an individual reasoning step is correct. This paper argues that the phrase "process supervision" is currently attached to three different target quantities, that the dominant scalable label defines the…

Cite Related research LOR-00071 · 5 views · 18 downloads

PDF444.5 KB

Journal article

A Step Score Is Not a Step Verdict: Three Quantities Under the Name Process Supervision, and the Outcome-Only Results That Make the Distinction Load-Bearing

Pranay M. Mahendrakar 2026

Process reward models are introduced, almost without exception, as models that score whether an individual reasoning step is correct. This paper argues that the phrase "process supervision" is currently attached to three different target quantities, that the dominant scalable label defines the…

Cite Related research LOR-00039 · 6 views · 9 downloads

PDF441.6 KB

Journal article

The Crossover Does Not Carry the Claim: Pass@k Inversion, the Reasoning Boundary, and Five Premises the RLVR Debate Leaves Unstated

Pranay M. Mahendrakar 2026

A model trained with reinforcement learning from verifiable rewards beats its base model at one sample and loses to it at many. The field has read that crossover as a measurement of the reasoning boundary and has spent two years arguing about which direction the boundary moved. This paper…

Cite Related research LOR-00072 · 7 views · 9 downloads

PDF461 KB

Journal article

The Crossover Does Not Carry the Claim: Pass@k Inversion, the Reasoning Boundary, and Five Premises the RLVR Debate Leaves Unstated

Pranay M. Mahendrakar 2026

A model trained with reinforcement learning from verifiable rewards beats its base model at one sample and loses to it at many. The field has read that crossover as a measurement of the reasoning boundary and has spent two years arguing about which direction the boundary moved. This paper…

Cite Related research LOR-00034 · 6 views · 29 downloads

PDF457.3 KB

5 records

Perspectives Without Independence: Multi-Agent and Multi-Persona Reasoning Under Compute-Normalised Comparison, Why the Gains That Survive Are Not the Ones Diversity Predicts, and the Controls That Would Tell Them Apart

A Step Score Is Not a Step Verdict: Three Quantities Under the Name Process Supervision, and the Outcome-Only Results That Make the Distinction Load-Bearing

A Step Score Is Not a Step Verdict: Three Quantities Under the Name Process Supervision, and the Outcome-Only Results That Make the Distinction Load-Bearing

The Crossover Does Not Carry the Claim: Pass@k Inversion, the Reasoning Boundary, and Five Premises the RLVR Debate Leaves Unstated

The Crossover Does Not Carry the Claim: Pass@k Inversion, the Reasoning Boundary, and Five Premises the RLVR Debate Leaves Unstated