AI Paper Atlas

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

Designing Observation and Action Models for Efficient Reinforcement Learning with LLMs

Deunsol Yoon, Sunghoon Hong, Whiyoung Jung, Junseok Park, Geon-Hyeong Kim, Woohyung Lim, Soonyoung Lee, Seung Hwan Kim, Kanghoon Lee

ICML 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents

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
add both observation and action models (full LOAM) instead of observation-only or action-only (ablation)LOAM · HumanoidBench basic locomotionreturn / convergence speedImproved
use Bayesian ridge regression acquisition instead of Gaussian process regression (ablation)LOAM-Race · HumanoidBench basic locomotionreturnNo clear effect
use racing instead of successive halving (SHA4, SHA8) for candidate allocation (ablation)LOAM-Race · HumanoidBench basic locomotionconvergence speedImproved
use UCB-style acquisition instead of always selecting current best candidate (CBS) (ablation)LOAM-Race · HumanoidBench basic locomotionreturnImproved
increase candidates from K=3 to K=4 (ablation)LOAM-Race · h1hand-cube, h1hand-insert_smallconvergence speedHurt
increase number of candidates K (up to 3) (ablation)LOAM-Race · h1hand-cube, h1hand-insert_smallperformance varianceImproved
add racing (LOAM-Race) when using smaller LLM backbones (GPT-5-nano, Qwen3-Coder-30B) (ablation)LOAM · HumanoidBench basic locomotionreturnImproved
replace GPT-5 with smaller LLMs in LOAM without racing (ablation)LOAM · HumanoidBench basic locomotionreturnHurt
apply LOAM design directly to raw observations rather than appending LLM features to handcrafted observations (LESR)FastTD3 · HumanoidBench run, hurdle, slide, pushreturnImproved
add LOAM-Race selection over single LOAM designLOAM · insert_small and cubeasymptotic returnMixed

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