Pith Number

pith:SR4SNW3A

pith:2026:SR4SNW3AAQVRBVENIKIIB5WAYR

not attested not anchored not stored refs resolved

Macro-Action Based Multi-Agent Instruction Following through Value Cancellation

Enrico Marchesini Xiang Zhi Tan, Ethan Rathbun, Wo Wei Lin

Correcting the Bellman backup target at each instruction boundary decouples value estimates across contexts, allowing a single policy to follow interrupting instructions while preserving base-task performance in multi-agent settings.

arxiv:2605.12655 v1 · 2026-05-12 · cs.AI · cs.MA

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{SR4SNW3AAQVRBVENIKIIB5WAYR}

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

MAVIC achieves high instruction compliance while preserving base task performance in increasingly complex cooperative multi-agent environments.

C2weakest assumption

That correcting the bootstrapping target at instruction boundaries is sufficient to fully decouple value estimates across contexts without introducing new inconsistencies under stochastic switching or macro-action interruptions.

C3one line summary

MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in a unified policy.

References

4 extracted · 4 resolved · 0 Pith anchors

[1] bring me the tomato, 2021

[2] When c=c ′, the reward is unchanged 1999

[3] Don’t use left cutting board 2022

[4] Go to small boxes 2022

Receipt and verification

First computed	2026-05-18T03:09:50.661167Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

947926db60042b10d48d429080f6c0c4639ef9fc6b35e048df11e7fe2a900836

Aliases

arxiv: 2605.12655 · arxiv_version: 2605.12655v1 · doi: 10.48550/arxiv.2605.12655 · pith_short_12: SR4SNW3AAQVR · pith_short_16: SR4SNW3AAQVRBVEN · pith_short_8: SR4SNW3A

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR \
  | 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: 947926db60042b10d48d429080f6c0c4639ef9fc6b35e048df11e7fe2a900836

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "13f9e0b6287753427bb2b64460e41c6fe500857010a03b3d0ec76c17189af15d",
    "cross_cats_sorted": [
      "cs.MA"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-12T19:01:16Z",
    "title_canon_sha256": "43132de58f7a27c4c4df01db7fb108f2740977bcc8221c99ca27420f797786e6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12655",
    "kind": "arxiv",
    "version": 1
  }
}