Skip to main content
Loading research indexW

LADDER: A Long-Horizon Robot Manipulation Benchmark

arxiv-cs.RO2026-10-13Source metadata onlyOpen source ↗
INVESTOR TAKEAWAY

General-purpose robot manipulation policies learn short-horizon skills effectively, but degrade rapidly on long-horizon tasks. Existing benchmarks cannot isolate failures because task horizon is either too short or entangled with scene and object variations.

ORIGINAL PAPER

LADDER: A Long-Horizon Robot Manipulation Benchmark

WHAT WE KNOW

We propose LADDER, a long-horizon robot manipulation benchmark scaling from 1 to 10 subgoals within the same environment over three suites (SimplerEnv-Long, RobotArena-$\infty$-Long, and RoboLab-Long), 145 tasks, eight categories, two embodiments, and 2,024 simulated episodes per system. We evaluate two orchestration paradigms: text subgoals for learned low-level policies (VoLo) and tool selection orchestration (CaP-X, GPT-Policy, PSP-Agent, TiPToP).

WATCH NEXT

Review the primary source, validate the main result, and establish whether any listed-company transmission is direct.

EVIDENCE

What the evidence supports so far

Research signals

Classification pending.

What remains unverified

The full methodology, effect size, and limitations still require analyst review.

Company impact remains unverified until a direct economic transmission is established.