SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.23258 · 2026

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

Liang Ding, Xuebo Liu, Yutong Wang, Min Zhang, Miao Zhang, Siyuan Xiong, Wenkang Zhou

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 0 have no contract verdict; 5 failures of our instrument; 1 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/2602.23258.json · badge: /api/ran/2602.23258.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
TonySY2/AgentDropoutV2 canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
aime_data_process Ran
ran; our contract draft was wrong, not the code
TonySY2/AgentDropoutV2/train/project_datasets/gsm8k_dataset.py
pointer only (licence: NONE) · get_code("10877d3b5ce4d019")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonySY2/AgentDropoutV2 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.

aqua_data_process Ran
ran; our contract draft was wrong, not the code
TonySY2/AgentDropoutV2/train/project_datasets/aqua_dataset.py
pointer only (licence: NONE) · get_code("86c8e223220fef12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonySY2/AgentDropoutV2 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.

delete_extra_zero Ran
ran; our contract draft was wrong, not the code
TonySY2/AgentDropoutV2/train/project_datasets/aqua_dataset.py
pointer only (licence: NONE) · get_code("1311b1da2c08b63b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonySY2/AgentDropoutV2 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.

gsm_data_process Ran
ran; our contract draft was wrong, not the code
TonySY2/AgentDropoutV2/train/project_datasets/gsm8k_dataset.py
pointer only (licence: NONE) · get_code("54b831c1e15e7821")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonySY2/AgentDropoutV2 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.

multiarith_data_process Ran
ran; our contract draft was wrong, not the code
TonySY2/AgentDropoutV2/train/project_datasets/gsm8k_dataset.py
pointer only (licence: NONE) · get_code("a7ce88cc86b22f0c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonySY2/AgentDropoutV2 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.

aqua_get_predict Not yet run
unverified (harvested, no recorded run)
TonySY2/AgentDropoutV2/train/project_datasets/aqua_dataset.py
pointer only (licence: NONE) · get_code("7f8c9ad1508a12f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TonySY2/AgentDropoutV2 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 4 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.

FunctionAlso present inEarliest-datedOthers named
delete_extra_zero 2 other papers
1 dated earlier, 1 later
2502.11133 (2025-02)
MasRouter: Learning to Route LLMs for Multi-Agent System
2609.02264 (2026-09)
Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems
gsm_data_process 2 other papers
1 dated earlier, 1 later
2502.11133 (2025-02)
MasRouter: Learning to Route LLMs for Multi-Agent System
2609.02264 (2026-09)
Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems

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

While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. Current solutions often resort to rigid structural engineering or expensive finetuning, limiting their adaptability. We propose AgentDropoutV2 (ADv2), a test-time rectifyor-reject pruning framework that dynamically optimizes MAS information flow. Acting as an active firewall, ADv2 intercepts agent outputs and employs a retrieval-augmented rectifier to iteratively correct errors. This rectification is guided by an indicator pool, which is constructed offline by distilling error patterns from historical MAS failure trajectories. Irreparable outputs are subsequently pruned to prevent error propagation. Empirical results demonstrate that ADv2 significantly boosts performance on both fixed and dynamic MAS frameworks, achieving average accuracy gains of 6.39 and 2.28 percentage points on extensive math and code benchmarks, respectively. Furthermore, ADv2 exhibits remarkable adaptivity, dynamically modulating rectification efforts based on task difficulty to resolve a wide spectrum of error patterns. Our code is released at https: //github.com/TonySY2/AgentDropoutV2.

For agents

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

get_harvested_code_for_paper("2602.23258")
get_code_for_paper("2602.23258")
have("2602.23258")

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

curl https://syntology.ai/api/ran/2602.23258.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.23258.svg)](https://syntology.ai/paper/2602.23258)

Connect an agent — have() is free.