Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

Multi-Agent Transactive Memory

To Eun Kim, Xuhong He, Dishank Jain, Ambuj Agrawal, Negar Arabzadeh, Fernando Diaz · Jun 18, 2026 · Citations: 0

General Multi Agent Simulation Env Web Browsing
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Moderate trust

Use this for comparison and orientation, not as your only source.

Best use

Background context only

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Moderate

Derived from extracted protocol signals and abstract evidence.

Abstract

The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations. Just as search engines index human-generated artifacts to support human problem solving, retrieval systems can organize agent-generated artifacts for reuse across agent populations. We extend retrieval-augmented generation - which demonstrates the value of human-authored artifacts to individual agents - to retrieval of agent-generated artifacts supporting a population of agents. In particular, agent trajectories encode reusable procedural knowledge, yet these artifacts are typically discarded after a single use or retained only by the producing agent, forcing newly instantiated agents to repeatedly rediscover existing solutions. We propose Multi-Agent Transactive Memory (MATM), a framework for population-level storage and retrieval of agent-generated trajectories, where producer agents contribute trajectories to a shared repository and consumer agents retrieve them to improve task execution. We focus on interactive environments (ALFWorld and WebArena), where trajectories are long and encode especially rich procedural structure. Our experiments demonstrate that retrieving trajectories from MATM improves downstream task performance and reduces interaction steps without coordination or joint training. These results position MATM as a design pattern for population-level experience sharing in open agent ecosystems.

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Usefulness score

27/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence 50%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations."

Evaluation Modes

strong

Simulation Env

Includes extracted eval setup.

"The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations."

Quality Controls

missing

Not reported

No explicit QC controls found.

"The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations."

Benchmarks / Datasets

strong

ALFWorld, WebArena

Useful for quick benchmark comparison.

"We focus on interactive environments (ALFWorld and WebArena), where trajectories are long and encode especially rich procedural structure."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations."

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Not reported
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Simulation Env
  • Agentic eval: Multi Agent, Web Browsing
  • Quality controls: Not reported
  • Evidence quality: Moderate
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

ALFWorldWebArena

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Metadata summary

The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations.
  • Just as search engines index human-generated artifacts to support human problem solving, retrieval systems can organize agent-generated artifacts for reuse across agent populations.
  • We extend retrieval-augmented generation - which demonstrates the value of human-authored artifacts to individual agents - to retrieval of agent-generated artifacts supporting a population of agents.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Research Summary

Contribution Summary

  • The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations.
  • Just as search engines index human-generated artifacts to support human problem solving, retrieval systems can organize agent-generated artifacts for reuse across agent populations.
  • We propose Multi-Agent Transactive Memory (MATM), a framework for population-level storage and retrieval of agent-generated trajectories, where producer agents contribute trajectories to a shared repository and consumer agents retrieve them…

Why It Matters For Eval

  • The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations.
  • We propose Multi-Agent Transactive Memory (MATM), a framework for population-level storage and retrieval of agent-generated trajectories, where producer agents contribute trajectories to a shared repository and consumer agents retrieve them…

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Simulation Env

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: ALFWorld, WebArena

  • Gap: Metric reporting is present

    No metric terms extracted.

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.