activity
20182026
collaborators

9 papers

cs.GT2026

Extrapolating Volition with Recursive Information Markets

Abhimanyu Pallavi Sudhir, Long Tran-Thanh

One of the impediments to the efficiency of information markets is the inherent information asymmetry present in them, exacerbated by the "buyer's inspection paradox" (the buyer ca…

cs.AI2025

A Benchmark for Scalable Oversight Protocols

Abhimanyu Pallavi Sudhir, Jackson Kaunismaa, Arjun Panickssery

As AI agents surpass human capabilities, scalable oversight -- the problem of effectively supplying human feedback to potentially superhuman AI models -- becomes increasingly criti…

cs.AI2025

Market-based Architectures in RL and Beyond

Abhimanyu Pallavi Sudhir, Long Tran-Thanh

Market-based agents refer to reinforcement learning agents which determine their actions based on an internal market of sub-agents. We introduce a new type of market-based algorith…

cs.LG2025

Consistency Checks for Language Model Forecasters

Daniel Paleka, Abhimanyu Pallavi Sudhir, Alejandro Alvarez +4

Forecasting is a task that is difficult to evaluate: the ground truth can only be known in the future. Recent work showing LLM forecasters rapidly approaching human-level performan…

cs.GT2024

Betting on what is neither verifiable nor falsifiable

Abhimanyu Pallavi Sudhir, Long Tran-Thanh

Prediction markets are useful for estimating probabilities of claims whose truth will be revealed at some fixed time -- this includes questions about the values of real-world event…

econ.TH2021

A mathematical definition of property rights in a Debreu economy

Abhimanyu Pallavi Sudhir

We present mathematical definitions for rights structures, government and non-attenuation in a generalized N-person game (Debreu abstract economy), thus providing a formal basis fo…