Pith Number

pith:FW7ADB3R

pith:2026:FW7ADB3RSNC6OPWWYJAQIEKTJF

not attested not anchored not stored refs pending

Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents

Bo Zhang, Jie Zhou, Liang He, Qin Chen, Wei Li, Xin Li, Yuxuan Cai

Lifelong agents learn an explicit policy for retrieving past experience only when it improves the next decision.

arxiv:2604.20572 v2 · 2026-04-22 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{FW7ADB3RSNC6OPWWYJAQIEKTJF}

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 on SciWorld, AlfWorld, and StuLife show that ProactAgent consistently improves lifelong agent performance, achieving success rates of 73.50% on SciWorld and 71.28% on AlfWorld while substantially reducing retrieval overhead, and attains performance competitive with proprietary models on StuLife.

C2weakest assumption

That comparing continuations from identical interaction prefixes with and without retrieval supplies unbiased, step-level supervision for the retrieval policy without introducing selection bias or reward hacking.

C3one line summary

ProactAgent learns a proactive retrieval policy via reinforcement learning on paired task continuations, improving lifelong agent performance and cutting retrieval overhead on SciWorld, AlfWorld, and StuLife.

Cited by

1 paper in Pith

Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning

Receipt and verification

First computed	2026-06-05T01:14:39.277588Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2dbe0187719345e73ed6c241041153494a4002ef49e91e88b192ec24a8d0e021

Aliases

arxiv: 2604.20572 · arxiv_version: 2604.20572v2 · doi: 10.48550/arxiv.2604.20572 · pith_short_12: FW7ADB3RSNC6 · pith_short_16: FW7ADB3RSNC6OPWW · pith_short_8: FW7ADB3R

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/FW7ADB3RSNC6OPWWYJAQIEKTJF \
  | 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: 2dbe0187719345e73ed6c241041153494a4002ef49e91e88b192ec24a8d0e021

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "24b3dba2d40e23bad40fbcadfa9276a427f16610a62637820fd0338a20c6b03c",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-22T13:50:55Z",
    "title_canon_sha256": "e23b7b0bb9a0366ba35570c56192f32eb233bd58a956db37f7065034a8374401"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.20572",
    "kind": "arxiv",
    "version": 2
  }
}