Pith Number

pith:EXB2TOYG

pith:2026:EXB2TOYG2COLC5L75WJOMENJMW

not attested not anchored not stored refs resolved

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents

Cihang Xie, Huaxiu Yao, Jiaqi Liu, Mingyu Ding, Peng Xia, Xinyu Ye, Zeyu Zheng

LLM agents can improve long-term memory by letting an LLM module diagnose retrieval failures and autonomously adjust the system's own configuration.

arxiv:2605.13941 v1 · 2026-05-13 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EXB2TOYG2COLC5L75WJOMENJMW}

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

EvolveMem outperforms the strongest baseline by 25.7% relative on LoCoMo and 18.9% on MemBench; evolved configurations transfer positively across benchmarks, indicating capture of universal retrieval principles.

C2weakest assumption

The LLM diagnosis module can reliably identify root causes of retrieval failures and propose configuration changes that improve performance without introducing new biases or regressions that the safeguards fail to catch.

C3one line summary

EvolveMem enables autonomous self-evolution of LLM memory retrieval configurations via LLM diagnosis and safeguards, delivering 25.7% gains over strong baselines on LoCoMo and 18.9% on MemBench with positive cross-benchmark transfer.

References

76 extracted · 76 resolved · 13 Pith anchors

[1] Self-rag: Learning to retrieve, generate, and critique through self-reflection 2024

[2] Self-play fine- tuning converts weak language models to strong language models 2024

[3] Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory 2025 · arXiv:2504.19413

[4] Über das gedächtnis: Untersuchungen zur experimentellen psychologie

[5] A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence 2025 · arXiv:2507.21046

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:13.854055Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

25c3a9bb06d09cb1757fed92e611a965a6266f6a882f8f651d4230a86e1fde73

Aliases

arxiv: 2605.13941 · arxiv_version: 2605.13941v1 · doi: 10.48550/arxiv.2605.13941 · pith_short_12: EXB2TOYG2COL · pith_short_16: EXB2TOYG2COLC5L7 · pith_short_8: EXB2TOYG

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/EXB2TOYG2COLC5L75WJOMENJMW \
  | 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: 25c3a9bb06d09cb1757fed92e611a965a6266f6a882f8f651d4230a86e1fde73

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2fd70656d7abd93ae21c86aa7c34bbdba70872b419e70b47dceed8038819da77",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T17:12:44Z",
    "title_canon_sha256": "88a871ec10fda027a57826b4ce3b05a0a76cd5e875f8dd7c7e9c7bd7c791f59a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13941",
    "kind": "arxiv",
    "version": 1
  }
}