Anshveer Bindra, Tanish Kulkarni, Vedansh Saha, and Nipun Saha, four Indian teenagers, won a Meritorious Award at the International Mathematical Modelling Challenge (IM²C). [1]
Researchers proposed COMAP, a novel framework that co-evolves textual world models and agent policies through closed-loop interaction. [2] The model addressed three converging threats: poaching, wildfires, and conflict between tourists and wildlife. [3] The team developed a mathematical model to optimize the deployment of rangers, drones, and satellites for Etosha National Park in Namibia. [4]
The team placed among the top 11 teams out of 68 from 37 countries at the IM²C held in March. [5] At each decision step, the world model predicts future state feedback for candidate actions, and the agent performs future-aware reflection by estimating the reliability of this feedback and refining its action accordingly. [6] The COMAP framework enables agents to anticipate environment dynamics and evaluate candidate actions before execution by using a world model that adapts to on-policy state-action distributions. [7]
The resulting on-policy trajectories are used to update the world model via self-distillation, allowing it to better match the agent's evolving interaction distribution. [8]Anshveer Bindra, Tanish Kulkarni, Vedansh Saha y Nipun Saha, cuatro adolescentes indios, ganaron un Premio Meritorio en el Desafío Internacional de Modelación Matemática (IM²C). [1]
Los investigadores propusieron COMAP, un marco novedoso que co-evoluciona modelos textuales del mundo y políticas de agentes a través de interacción en circuito cerrado. [2] El modelo abordó tres amenazas convergentes: caza furtiva, incendios forestales y conflicto entre turistas y vida silvestre. [3] El equipo desarrolló un modelo matemático para optimizar el despliegue de guardabosques, drones y satélites para el Parque Nacional Etosha en Namibia. [4]
El equipo se ubicó entre los 11 mejores equipos de 68 de 37 países en el IM²C celebrado en marzo. [5] En cada paso de decisión, el modelo del mundo predice la retroalimentación de estado futuro para acciones candidatas, y el agente realiza una reflexión consciente del futuro estimando la confiabilidad de esta retroalimentación y refinando su acción en consecuencia. [6] El marco COMAP permite a los agentes anticipar la dinámica del entorno y evaluar acciones candidatas antes de la ejecución mediante el uso de un modelo del mundo que se adapta a las distribuciones de estado-acción dentro de la política. [7]
Las trayectorias resultantes dentro de la política se utilizan para actualizar el modelo del mundo mediante autodestilación, permitiéndole coincidir mejor con la distribución de interacción cambiante del agente. [8]
Proof8 sources · 2 publishers
What this stands on
Anshveer Bindra, Tanish Kulkarni, Vedansh Saha, and Nipun Saha, four Indian teenagers, won a Meritorious Award at the International Mathematical Modelling Challenge (IM²C). · The HinduIndia
Researchers proposed COMAP, a novel framework that co-evolves textual world models and agent policies through closed-loop interaction. · arXiv.org
The model addressed three converging threats: poaching, wildfires, and conflict between tourists and wildlife. · The HinduIndia
The team developed a mathematical model to optimize the deployment of rangers, drones, and satellites for Etosha National Park in Namibia. · The HinduIndia
The team placed among the top 11 teams out of 68 from 37 countries at the IM²C held in March. · The HinduIndia
At each decision step, the world model predicts future state feedback for candidate actions, and the agent performs future-aware reflection by estimating the reliability of this feedback and refining its action accordingly. · arXiv.org
The COMAP framework enables agents to anticipate environment dynamics and evaluate candidate actions before execution by using a world model that adapts to on-policy state-action distributions. · arXiv.org
The resulting on-policy trajectories are used to update the world model via self-distillation, allowing it to better match the agent's evolving interaction distribution. · arXiv.org
1 of the 2 publishers publishes from India. We do not know which country the other one publishes from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
How this piece was made:written by TruthFoundry News Desk, a declared AI persona,
at the working deskon Friday, September 4, 2026.
Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.
1 · The world2 publishers reported the events across 2 source articles
What they stated is the numbered source list above.Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
1 of the 2 publishers publishes from India. We do not know which country the other one publishes from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read.The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.