AI Paper Atlas

Research map / Large language models / Agents, code and math

Automated Human Strategic Behavior Modeling via Large Language Models

Xiaohan Xie, Haoran Yu, Biying Shou, Jianwei Huang

AAAI 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 0 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
use AutoBM (structured spec + hybrid search) instead of BoxLMLLM model search · Ultimatum game (proposer, test)NLL: 5.476 -> 5.306Improved
use AutoBM instead of FunSearchLLM model search · Ultimatum game (proposer, test)NLL: 5.608 -> 5.306Improved
replace human-crafted ERC/IA/QRE with LLM-generated modelsbehavioral models · Ultimatum game (proposer, test)NLL: 5.954 -> 5.306Improved
apply a single round of LLM judgment and refinement to human-crafted models (J&I)human-crafted models · Ultimatum game (proposer, test)NLL: 5.954 -> 5.724Improved
use AutoBM instead of BoxLMLLM model search · Repeated rock-paper-scissors (test)accuracy (%): 37.94 -> 44.29Improved
use AutoBM instead of FunSearchLLM model search · Repeated rock-paper-scissors (test)NLL: 1.094 -> 1.074Improved
single-round LLM refinement of human baselines (J&I)human-crafted models · Repeated rock-paper-scissors (test)NLL: 1.092 vs 1.095No clear effect
use AutoBM instead of FunSearchLLM model search · Continuous double auctions (buyer bids, test)NLL: 4.986 -> 4.788Improved
use AutoBM instead of BoxLMLLM model search · Continuous double auctions (buyer bids, test)MSE: 0.0520 -> 0.0450Improved
replace belief-based/time-dependent bidding with J&I-refined modelhuman-crafted models · Continuous double auctions (buyer bids, test)NLL: 6.037 -> 5.652Improved
add exploration mechanism (AutoBM, FunSearch) vs propose-criticize only (BoxLM)LLM model search · Continuous double auctions (buyer bids, test)NLL convergenceImproved
add LLM judgment and structured representation on top of evolutionary searchAutoBM vs FunSearch · Continuous double auctions (buyer bids, test)final NLL: 4.986 -> 4.788Improved

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