SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.24693 · 2026

CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming

Jia Li, Yuhan Li, Peisong Wang, Bowen Liu, Yuyao Wang, Zehua Li, Zhiwei Ma

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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; 6 failures of our instrument; 3 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/2605.24693.json · badge: /api/ran/2605.24693.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
NineAbyss/CP-Agent canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
compile_source_code Ran
ran; our contract draft was wrong, not the code
NineAbyss/CP-Agent/ICPC-Eval/SubmitProblem_local.py
pointer only (licence: NONE) · get_code("19e7116835600785")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

create_llm_instance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
NineAbyss/CP-Agent/LiveCodeBench-Pro/benchmark_parallel.py
pointer only (licence: NONE) · get_code("fa9ab3c6cfa56241")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

get_metrics Ran
ran; our contract draft was wrong, not the code
NineAbyss/CP-Agent/LiveCodeBench-Pro/get_metrics.py
pointer only (licence: NONE) · get_code("787a0fde31eb9f2e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

load_evaluation_report Ran
ran; our contract draft was wrong, not the code
NineAbyss/CP-Agent/ICPC-Eval/eval_local.py
pointer only (licence: NONE) · get_code("cba8d3a9ce5fb505")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

normalize_output Ran
ran; our contract draft was wrong, not the code
NineAbyss/CP-Agent/ICPC-Eval/SubmitProblem_local.py
pointer only (licence: NONE) · get_code("29f694583b214b5d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

run_with_limits Ran
ran on a synthesized input
NineAbyss/CP-Agent/ICPC-Eval/SubmitProblem_local.py
pointer only (licence: NONE) · get_code("89365f39b8af67a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

submit_code_with_retry Ran
ran; our contract draft was wrong, not the code
NineAbyss/CP-Agent/ICPC-Eval/eval_agent.py
pointer only (licence: NONE) · get_code("3f77dedb719a73dc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

process_problem Not yet run
unverified (harvested, no recorded run)
NineAbyss/CP-Agent/ICPC-Eval/eval_agent.py
pointer only (licence: NONE) · get_code("f884f7918e45ae14")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

setup_logger Not yet run
unverified (harvested, no recorded run)
NineAbyss/CP-Agent/ICPC-Eval/eval_agent.py
pointer only (licence: NONE) · get_code("09292f0fa3c55e22")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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.

setup_logging Not yet run
unverified (harvested, no recorded run)
NineAbyss/CP-Agent/agentflow/main_agent.py
pointer only (licence: NONE) · get_code("0aeca2b1d78fe74b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NineAbyss/CP-Agent 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We study when execution feedback reliably helps an LLM CP solver and which mechanisms govern the gains. We model feedback-driven solving as a calibrated stopped process and identify three quantities: falseadmission risk, program-level evidence against bad programs, and the active-state success hazard. Under held-out trace calibration and selection from a pre-declared finite controller manifest, the resulting structural certificate lower-bounds the clean success probability before false admission. We instantiate mechanisms targeting these quantities as Dual-Granularity Verification, Test Augmentation, and Experience-Driven Self-Evolving, yielding CP-Agent. Without updating any parameters, CP-Agent raises Pass@1 from 25.8% to 48.5% on LiveCodeBench Pro and improves Refine@5 by 11.0% on ICPC-Eval. Across three LLM backbones, CP-Agent lies on the cost-accuracy efficiency frontier, and ablations show that each component primarily affects its corresponding certificate quantity. • Computing methodologies → Natural language processing; • Mathematics of computing → Stochastic processes.

For agents

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

get_harvested_code_for_paper("2605.24693")
get_code_for_paper("2605.24693")
have("2605.24693")

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

curl https://syntology.ai/api/ran/2605.24693.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.24693.svg)](https://syntology.ai/paper/2605.24693)

Connect an agent — have() is free.