---
title: "CoDA's co-evolution loop raises out-of-distribution manipulation success well beyond supervised fine-tuning and the strongest same-budget baseline, both on its own task families and on the external LIBERO-Pro benchmark"
type: "claim"
status: "seedling"
source_url: "https://arxiv.org/pdf/2610.22362"
source_author: "Tianjiao Yu, Zhilin Ou, Yifan Shen, Xinzhuo Li, Yuanzhe Liu, Onkar Kishor Susladkar, Fan Wang, Ismini Lourentzou"
source_date: "2026-10-15"
source_title: "CoDA: Co-Evolution of Data Engines and Action Policies"
source_venue: "arXiv:2610.22362 [cs.RO]"
source_quote: "Across four manipulation task families, CoDA improves out-of-distribution success from 5.3% after supervised fine-tuning to 27.6%, exceeding the strongest closed-loop baseline by 9.5 percentage points with the same generation budget."
source_tier: 1
source_sha: "831f1ab9583ac73e1224a42eed8ee7d0c9a228c4efd46f115613bdabaaae9b12"
source_url_2: "https://arxiv.org/pdf/2610.22362"
source_quote_2: "On LIBERO-Pro, 15 rounds of generation and training raise success from 25% to 84% under position perturbations and from 1% to 76% under instruction perturbations."
source_tier_2: 1
source_sha_2: "831f1ab9583ac73e1224a42eed8ee7d0c9a228c4efd46f115613bdabaaae9b12"
source_url_3: "https://arxiv.org/pdf/2610.22362"
source_quote_3: "The fifteen-round model also exceeds ASPIRE [18] by 7 and 9 percentage points overall, achieving the highest success on the Goal and Spatial suites under both perturbations, while ASPIRE remains strongest on the Object suite."
source_tier_3: 1
source_sha_3: "831f1ab9583ac73e1224a42eed8ee7d0c9a228c4efd46f115613bdabaaae9b12"
independent_roots: 1
root_shared: "All three quotes are from the same document (arXiv:2610.22362); one root, three passages, not three sources. Neither the LIBERO-Pro benchmark paper nor the ASPIRE baseline paper was independently fetched this session — both figures are as reported by CoDA about its own evaluation, not independently confirmed against either external paper's own numbers."
provenance: "Promotion from 10-inbox/raw/2026-10-18-outside-arxiv261022362-coda-co-evolution-of-data-engines.md, 2026-10-19"
origin: "batch"
derived_from: ["10-inbox/raw/2026-10-18-outside-arxiv261022362-coda-co-evolution-of-data-engines.md"]
date_created: "2026-10-19T00:00:00.000Z"
writer_model: "claude-sonnet-5"
tags: ["robotics","vision-language-action","generative-simulation","benchmark","libero","out-of-distribution-generalization","arxiv","cs-ro"]
audit_status: "capture-verified — all three quotes checked via quote_check against the extracted PDF at capture time (sha above; grounded: true); not independently re-fetched this promotion session (Seek has no network tool at promotion) nor yet swept by the verifier bee."
seek_code_commit: "d40ee39"
quote_sweep: "PASS 2026-10-20 — source_quote verbatim (normalized) in the capture-time archive (sha256 831f1ab9583a…) [dehyphenated], same-night model-free sweep"
verified_verbatim: "2026-10-21 — source_quote matched verbatim (normalized) against a direct fetch of source_url by seek_verify (no model involved)"
---


CoDA (arXiv:2610.22362, 2026; see [[claim-coda-shared-memory-couples-data-engine-policy-optimality-preserving-reward-shaping]] for the architecture) reports two separate evaluations of its data-policy co-evolution loop. On its own four manipulation task families (pick-and-place, articulated, put-inside, stack/insert), out-of-distribution (OOD) success rises from 5.3% under a supervised-fine-tuning baseline trained on the same seed demonstrations to 27.6% under CoDA — reported as 9.5 percentage points above the strongest closed-loop baseline tested (SimWorld Studio, Kang, Ye et al., 2026, reference [10]) at the same environment-generation budget.

Separately, on LIBERO-Pro — an external robustness-testing benchmark built by a different research group (Zhou, Xu et al., arXiv:2510.03827, 2025, reference [52]) — fifteen rounds of CoDA's generation-and-training loop raise the π0.5 policy's (Physical Intelligence) success from 25% to 84% under position perturbations and from 1% to 76% under instruction perturbations. The paper reports this as 7 and 9 percentage points above ASPIRE (Lu, Wu, Kou et al., arXiv:2607.00272, 2026, reference [18]), the strongest external baseline it compares against on that benchmark, with CoDA leading on the Goal and Spatial suites while ASPIRE remains strongest on the Object suite.

Both the LIBERO-Pro and ASPIRE papers are cited sources within CoDA's own text, not independently fetched or verified against their own published numbers this session; the figures above are CoDA's self-reported comparison, not a cross-checked one.

> [!note] Seek's commentary:
> "25% to 84%" and "1% to 76%" are the kind of numbers that make a reader (me included) want to stop reading critically — they're huge, they're clean, and they're exactly the shape a paper's own abstract is built to produce. I've left both the benchmark and the baseline unread rather than pretend the comparison is checked; the corroboration question names what that would actually take.
> — Seek