pith. sign in
Pith Number

pith:FNN4BC7A

pith:2026:FNN4BC7ATDAHTUA3IXS3MDSQ6S
not attested not anchored not stored refs pending

Reward Shaping and Action Masking for Compositional Tasks using Behavior Trees and LLMs

Ankita Samaddar, Nicholas Potteiger, Taylor T. Johnson, Xenofon Koutsoukos

MRBTs generated by LLMs and verified by SMT solvers deliver reactive reward shaping plus action masking for compositional RL tasks.

arxiv:2605.05795 v2 · 2026-05-07 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{FNN4BC7ATDAHTUA3IXS3MDSQ6S}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Experiments demonstrate successful generation and refinement of five MRBTs, consistently improving training efficiency and task success rates over baselines and MRBTs without action masking.

C2weakest assumption

That LLMs can reliably produce MRBTs that remain correct and modular across varying task objects, and that the derived logical specifications fully capture reactivity to subtask failure without missing edge cases.

C3one line summary

MRBTs generated via LLMs and verified by SMT solvers deliver modular, reactive reward shaping and action masking that improves RL training efficiency and success rates on compositional tasks.

Receipt and verification
First computed 2026-05-26T01:03:32.532198Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

2b5bc08be098c079d01b45e5b60e50f49725043afd7d4e7a7ef6498b355b44de

Aliases

arxiv: 2605.05795 · arxiv_version: 2605.05795v2 · doi: 10.48550/arxiv.2605.05795 · pith_short_12: FNN4BC7ATDAH · pith_short_16: FNN4BC7ATDAHTUA3 · pith_short_8: FNN4BC7A
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/FNN4BC7ATDAHTUA3IXS3MDSQ6S \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 2b5bc08be098c079d01b45e5b60e50f49725043afd7d4e7a7ef6498b355b44de
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "757bfb908689a4aa58296cbda02a83c2b77526b5cc9d41cb3c5c1f62f5f82434",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-07T07:33:08Z",
    "title_canon_sha256": "d254cb3e2c0fd7e68a776032074eefcc034387dba24834339a2746dcf27f921c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.05795",
    "kind": "arxiv",
    "version": 2
  }
}