SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.13840 · ICML · 2026

PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training

Yiran Chen, Hai Li, Jingwei Sun, Hancheng Ye, Yuhan Cheng

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure 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/2602.13840.json · badge: /api/ran/2602.13840.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
chengyh23/PrivAct community
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
TreeNode Ran
ran on a synthesized input · constructed an object; no result was computed
chengyh23/PrivAct/src/preference_pairs_MA.py
pointer only (licence: NONE) · get_code("e65488a0ff09e2e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengyh23/PrivAct 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.

cartesian_product Ran
ran; our contract draft was wrong, not the code
chengyh23/PrivAct/src/preference_pairs_MA.py
pointer only (licence: NONE) · get_code("669afe2d1c71b9de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengyh23/PrivAct 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.

collect_preference_pairs_from_tree Ran
ran, honoured the contract we drafted
chengyh23/PrivAct/src/preference_pairs_MA.py
pointer only (licence: NONE) · get_code("53db6caa216111a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengyh23/PrivAct 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.

MultiAgentTree Not yet run
unverified (harvested, no recorded run)
chengyh23/PrivAct/src/preference_pairs_MA.py
pointer only (licence: NONE) · get_code("681c0442e18877dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, chengyh23/PrivAct 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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 model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy. Existing approaches rely on external, inference-time interventions which are brittle, scenario-specific, and may expand the privacy attack surface. We propose PrivAct, a contextual privacy-aware multiagent learning framework that internalizes contextual privacy preservation directly into models' generation behavior for privacy-compliant agentic actions. By embedding privacy preferences into each agent, PrivAct enhances systemwide contextual integrity while achieving a more favorable privacy-helpfulness tradeoff. Experiments across multiple LLM backbones and benchmarks demonstrate consistent improvements in contextual privacy preservation, reducing leakage rates by up to 12.32% while maintaining comparable helpfulness, as well as zero-shot generalization and robustness across diverse multiagent topologies. Code is available at https: //github.com/chengyh23/PrivAct.

For agents

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

get_harvested_code_for_paper("2602.13840")
get_code_for_paper("2602.13840")
have("2602.13840")

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

curl https://syntology.ai/api/ran/2602.13840.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.13840.svg)](https://syntology.ai/paper/2602.13840)

Connect an agent — have() is free.