SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.01485 · 2026

Predicting and improving test-time scaling laws via reward tail-guided search

Jian Qian, Muheng Li, Wenlong Mou

arXiv · PDF · Open in the Atlas

Code that ran

5 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 4 failures of our instrument; 11 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.01485.json · badge: /api/ran/2602.01485.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
PotatoJnny/Scaling-Law-Guided-search community
Papers with Code archive
5 ran · 11 no recorded run
FunctionStatusWhere it lives
State Ran
ran on a synthesized input
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("149f1b3dd419c067")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_clean_and_post_process Ran
ran; our contract draft was wrong, not the code
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("97f46db6eb9c6eb9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_clean_single_step_for_proof Ran
ran; our contract draft was wrong, not the code
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("d1f2df5c4171cb59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

clean_and_truncate_at_eor Ran
ran; our contract draft was wrong, not the code
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("5b6168dc2d299da7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_model_answer Ran
ran; our contract draft was wrong, not the code
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("d5ef3d93d1f22f1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Action Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("23702e4dd78af8de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LLMWrapper Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("bcb42e94b0bcb028")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LMConfig Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("1d4084585ada7212")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Node Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("d103b68321fb85fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

RMConfig Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("0f881bfede592236")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

RMWrapper Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("0822682e53aa1af9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

SLGConfig Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("ab69b63f36467e12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

SLG_Search Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("2e55716761f6833b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_process_job Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("5623847dc5484170")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_worker_loop Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("ca0cdf4bd833efc9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

work_on_last_step Not yet run
unverified (harvested, no recorded run)
PotatoJnny/Scaling-Law-Guided-search/Algorithm/algorithms.py
pointer only (licence: NONE) · get_code("d26e5bb54dbf046f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PotatoJnny/Scaling-Law-Guided-search when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 16 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Test-time scaling has emerged as a critical avenue for enhancing the reasoning capabilities of Large Language Models (LLMs). Though the straight-forward "best-of-N " (BoN) strategy has already demonstrated significant improvements in performance, it lacks principled guidance on the choice of N , budget allocation, and multi-stage decision-making, thereby leaving substantial room for optimization. While many works have explored such optimization, rigorous theoretical guarantees remain limited. In this work, we propose new methodologies to predict and improve scaling properties via tail-guided search. By estimating the tail distribution of rewards, our method predicts the scaling law of LLMs without the need for exhaustive evaluations. Leveraging this prediction tool, we introduce Scaling-Law Guided (SLG) Search, a new test-time algorithm that dynamically allocates compute to identify and exploit intermediate states with the highest predicted potential. We theoretically prove that SLG achieves vanishing regret compared to perfectinformation oracles, and achieves expected rewards that would otherwise require a polynomially larger compute budget required when using BoN. Empirically, we validate our framework across different LLMs and reward models, confirming that tail-guided allocation consistently achieves higher reward yields than Best-of-N under identical compute budgets. Our code is available at https://github.com/PotatoJnny/Scaling-Law-Guided-search.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.01485")
get_code_for_paper("2602.01485")
have("2602.01485")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.01485.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.01485.svg)](https://syntology.ai/paper/2602.01485)

Connect an agent — have() is free.