Org-Agent: Beyond Personal Assistants Towards Organizational Agents

Hugging Face Daily Papers Papers
multi-agent-systems organizational-agents constraint-reasoning knowledge-memory task-scheduling llm-agents

Summary

The paper introduces Org-Agent, a unified constraint-centric reasoning framework that enables LLM agents to coordinate requests from multiple users and use knowledge distributed across interactions, decomposing tasks via dependency graphs and topological scheduling. Experiments on MUSES-Bench and GroupMemBench show gains in cross-user decision-making and memory capabilities.

Language model agents serving organizations must coordinate requests from multiple users while using knowledge distributed across their interactions. We identify two complementary capabilities for this setting, namely cross-user interaction and decision-making, as well as cross-user memory and knowledge use. Both capabilities are governed by organizational constraints across three aspects: user identity, authority, and access permissions; the attribution and temporal validity of information; and rules for resolving conflicting requirements across users and completion requirements for joint decisions. These constraints shape what information or decisions must be obtained before an action can proceed and what conditions must be satisfied during its execution. Motivated by this, we introduce Org-Agent, a unified constraint-centric reasoning framework that organizes task execution in three stages. Specifically, Org-Agent decomposes a task into atomic subtasks and constructs a task dependency graph whose edges encode the dependencies among them. Building on this graph, it schedules the subtasks in dependency order through topological sorting. It then executes each subtask while accounting for the task's constraints, supported by evidence-acquisition and memory-management tools. Experiments on MUSES-Bench and GroupMemBench demonstrate the effectiveness of Org-Agent on both capabilities, and ablations further support the contributions of dependency modeling and tool use.
Original Article
View Cached Full Text

Cached at: 09/30/26, 08:18 PM

Paper page - Org-Agent: Beyond Personal Assistants Towards Organizational Agents

Source: https://huggingface.co/papers/2609.34392

Abstract

Languagemodelagentsservingorganizationsmustcoordinaterequestsfrommultipleuserswhileusingknowledgedistributedacrosstheirinteractions.Weidentifytwocomplementarycapabilitiesforthissetting,namelycross-userinteractionanddecision-making,aswellascross-usermemoryandknowledgeuse.Bothcapabilitiesaregovernedbyorganizationalconstraintsacrossthreeaspects:useridentity,authority,andaccesspermissions;theattributionandtemporalvalidityofinformation;andrulesforresolvingconflictingrequirementsacrossusersandcompletionrequirementsforjointdecisions.Theseconstraintsshapewhatinformationordecisionsmustbeobtainedbeforeanactioncanproceedandwhatconditionsmustbesatisfiedduringitsexecution.Motivatedbythis,weintroduceOrg-Agent,aunifiedconstraint-centricreasoningframeworkthatorganizestaskexecutioninthreestages.Specifically,Org-Agentdecomposesataskintoatomicsubtasksandconstructsataskdependencygraphwhoseedgesencodethedependenciesamongthem.Buildingonthisgraph,itschedulesthesubtasksindependencyorderthroughtopologicalsorting.Itthenexecuteseachsubtaskwhileaccountingforthetask’sconstraints,supportedbyevidence-acquisitionandmemory-managementtools.ExperimentsonMUSES-BenchandGroupMemBenchdemonstratetheeffectivenessofOrg-Agentonbothcapabilities,andablationsfurthersupportthecontributionsofdependencymodelingandtooluse.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2609\.34392

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.34392 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.34392 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.34392 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows

arXiv cs.AI

AgentCo-op is a retrieval-based synthesis framework for composing interoperable multi-agent workflows from reusable skills, tools, and external agents. It uses typed artifact handoffs and bounded self-guided local repair, achieving strong results on benchmarks and enabling collaborative discovery in open-world genomics tasks.

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

Hugging Face Daily Papers

The paper presents ABot-AgentOS, a general robotic agent operating system with lifelong multi-modal memory, and introduces EmbodiedWorldBench for evaluating long-horizon embodied tasks. It demonstrates significant improvements in task success and memory benchmarks, suggesting that a dedicated agent OS layer enhances execution and persistent memory.

Organizational Memory for Agentic Business Process Execution

arXiv cs.AI

This paper proposes an organizational memory architecture for LLM-based agents to execute business processes using shared, organization-specific knowledge, addressing the scalability and consistency challenges of per-agent knowledge encoding.

Rethinking Multi-Agent Collaboration: When More Is Less

arXiv cs.AI

This paper delineates the capability boundaries of multi-agent collaboration in LLM-based systems, showing benefits only in specific task structures like long-horizon tasks with sparse dependencies, and proposes SAIGE, a dynamic graph-based mechanism for efficient collaboration.

COOPA: A Modular LLM Agent Architecture for Operations Research Problems

arXiv cs.LG

This paper introduces COOPA, a modular LLM agent architecture for operations research problems that combines iterative confidence-based modeling, element-level provenance, and multi-solver routing. Evaluated across eight LLM backbones and four baselines, COOPA achieves the best macro-average accuracy on six backbones and improves over the strongest baseline by up to 6.7 percentage points.