Pith Number

pith:7JHGNWME

pith:2026:7JHGNWMEYH5MUOX4NK37ME2ZTH

not attested not anchored not stored refs resolved

EXG: Self-Evolving Agents with Experience Graphs

Hanchen Wang, Lu Qin, Siyuan Zhang, Wenjie Zhang, Ying Zhang, Yuxin Jin

EXG turns agent successes and failures into a connected graph for instant reuse across tasks.

arxiv:2605.17721 v1 · 2026-05-18 · 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{7JHGNWMEYH5MUOX4NK37ME2ZTH}

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

EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module.

C2weakest assumption

That successes and failures accumulated during agent execution can be effectively captured and related in a graph structure that enables immediate and transferable reuse without fragmentation or high overhead, as positioned against ad hoc reflection and unstructured memory in the abstract.

C3one line summary

EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.

References

56 extracted · 56 resolved · 19 Pith anchors

[1] MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems 2025 · arXiv:2510.17281

[2] FLEX: Continuous agent evolution via forward learning from experience 2025

[3] Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution 2025 · arXiv:2512.10696

[4] Evaluating Large Language Models Trained on Code 2021 · arXiv:2107.03374

[5] Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, and Ningyu Zhang

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:04:54.752182Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fa4e66d984c1faca3afc6ab7f6135999eff337b75ff4d05ec414765328fc0b03

Aliases

arxiv: 2605.17721 · arxiv_version: 2605.17721v1 · doi: 10.48550/arxiv.2605.17721 · pith_short_12: 7JHGNWMEYH5M · pith_short_16: 7JHGNWMEYH5MUOX4 · pith_short_8: 7JHGNWME

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/7JHGNWMEYH5MUOX4NK37ME2ZTH \
  | 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: fa4e66d984c1faca3afc6ab7f6135999eff337b75ff4d05ec414765328fc0b03

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ae0bb3398c8e4d58bd1672119b639ce3244c9a16f87f9f2b63154c5c7d459eb3",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-18T00:50:23Z",
    "title_canon_sha256": "844b992d5f99c159fcee93aaf09b8a383b20db22f0f4365b69b7274bc202854c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.17721",
    "kind": "arxiv",
    "version": 1
  }
}