AI Paper Atlas

Research map / Large language models / AI and society

Modeling Others' Minds as Code

Kunal Jha, Aydan Yuenan Huang, Eric Ye, Natasha Jaques, Max Kleiman-Weiner

ICLR 2026 · Large language models › AI and society · approach: Human-centered trust and agency · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
model agent as synthesized Python program with Bayesian reweighting instead of naive LLM promptingNLLM · Construction scripted, multi-stepaccuracy: 0.310 -> 0.479Improved
use ROTE instead of NLLM on human gameplayNLLM · Construction human, multi-stepaccuracy: 0.151 -> 0.296Improved
use ROTE instead of NLLM on PartnrNLLM · Partnr single-stepaccuracy: 0.113 -> 0.537Improved
add two-stage observation parsing (ablation)ROTE · Partnr single-stepaccuracy: 0.537 -> 0.160Hurt
add two-stage observation parsing (ablation)ROTE · Construction scripted and humanaccuracy: 0.479 -> 0.522 scriptedNo clear effect
enforce strict FSM structure (severe) instead of light (ablation)ROTE · Partnr single-stepaccuracy: 0.537 -> 0.440Hurt
use moderate structure instead of light (ablation)ROTE · Construction humanaccuracy: 0.296 -> 0.310Improved
use SMC with rejuvenation instead of importance sampling (ablation)ROTE · small hypothesis budgetsearly accuracyMixed
vary top-k pruning (1, 10, 30) (ablation)ROTE · ConstructionaccuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy