MétaCan
Menu
Back to cohort
Record W2036236783 · doi:10.1145/860575.860808

Overcoming agent delusion

2003· article· en· W2036236783 on OpenAlexaff
Olayide Olorunleke, Gordon McCalla

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicMulti-Agent Systems and Negotiation
Canadian institutionsUniversity of Saskatchewan
Fundersnot available
KeywordsGossipDelusionComputer scienceAgent architectureMulti-agent systemAgent-based modelPsychotropic AgentArchitectureArtificial intelligencePsychologySocial psychology

Abstract

fetched live from OpenAlex

Agent models are internal representations held by an agent of itself and of other agents in its environment. Agent modelling is necessary for coordinating and individualizing the actions of agents. An important goal is that agents not be deluded about each other, that is, that there is no incompatibility between an agent's models and the actual properties of the agents being modeled. This paper is about overcoming such delusion, in particular with strategies that rely on interactions and gossip between an agent and other agents. We present a number of studies of the effectiveness of these strategies and the trade-offs among them. These studies have been carried out using an agent architecture and a simulation environment both specifically designed to allow exploration of agent modelling issues.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.052
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.010
Threshold uncertainty score0.052

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.052
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0020.004
Scholarly communication0.0040.009
Open science0.0020.012
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0050.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.028
GPT teacher head0.251
Teacher spread0.223 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2003
Admission routes1
Has abstractyes

Explore more

Same topicMulti-Agent Systems and NegotiationFrench-language works237,207