SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.02518 · 2026

GRAPHDANCER: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training

Yu Wang, Yu Zhang, Jianwen Xie, Yuyang Bai, Zhuofeng Li, Ping Nie

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.02518.json · badge: /api/ran/2602.02518.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
leopoldwhite/GraphDancer canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
em_check Ran
ran, honoured the contract we drafted
leopoldwhite/GraphDancer/verl/utils/reward_score/graphdancer_qa_em.py
pointer only (licence: NONE); the stored copy get_code serves, from TencentBAC/ReSeek, is pointer only (licence: NONE) · get_code("f8ea5de03c824510")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_config_from_args Ran
ran; our contract draft was wrong, not the code
leopoldwhite/GraphDancer/verl/model_merger/base_model_merger.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("8896f4e2bafe8abc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_dynamic_pipeline_shards Ran
ran, honoured the contract we drafted
leopoldwhite/GraphDancer/verl/model_merger/megatron_model_merger.py
pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("94209884dcb2308e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_huggingface_actor_config Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
leopoldwhite/GraphDancer/verl/utils/model.py
pointer only (licence: NONE); the stored copy get_code serves, from Qwen-Applications/CLIPO, is pointer only (licence: NONE) · get_code("1ac72f97fbbef4f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_answer Ran
ran; our contract draft was wrong, not the code
leopoldwhite/GraphDancer/verl/utils/reward_score/graphdancer_qa_em.py
pointer only (licence: NONE); the stored copy get_code serves, from shmsw25/GraphRetriever, is pointer only (licence: NONE) · get_code("dae7ab386661a4f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_graph_call Ran
ran; our contract draft was wrong, not the code
leopoldwhite/GraphDancer/graphdancer/llm_agent/generation_graph.py
pointer only (licence: NOASSERTION) · get_code("a9734e0712e85556")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, leopoldwhite/GraphDancer (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

remove_quotes Ran
ran; our contract draft was wrong, not the code
leopoldwhite/GraphDancer/graphdancer/llm_agent/generation_graph.py
pointer only (licence: NOASSERTION) · get_code("1540ac9f3c6d1d00")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, leopoldwhite/GraphDancer (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

split_two_args Ran
ran; our contract draft was wrong, not the code
leopoldwhite/GraphDancer/graphdancer/llm_agent/generation_graph.py
pointer only (licence: NOASSERTION) · get_code("9a9543fd2aa23d16")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, leopoldwhite/GraphDancer (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

subem_check Ran
ran, honoured the contract we drafted
leopoldwhite/GraphDancer/verl/utils/reward_score/graphdancer_qa_em.py
pointer only (licence: NONE) · get_code("eb94037d0866de26")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

unpad_dataproto Ran
ran; our contract draft was wrong, not the code
leopoldwhite/GraphDancer/verl/protocol.py
pointer only (licence: NONE) · get_code("83b1686d7ac03c21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_generation_config Not yet run
unverified (harvested, no recorded run)
leopoldwhite/GraphDancer/verl/utils/model.py
pointer only (licence: NONE); the stored copy get_code serves, from Qwen-Applications/CLIPO, is pointer only (licence: NONE) · get_code("319697b76561a1e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

squeeze Not yet run
unverified (harvested, no recorded run)
leopoldwhite/GraphDancer/verl/utils/model.py
pointer only (licence: NONE) · get_code("3b15e2ac7497c441")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leopoldwhite/GraphDancer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 9 the same month, 9 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
normalize_answer 133 other papers
120 dated earlier, 4 the same month, 8 later, 1 undated · 1 only as an assembly brick
1508.06615 (2015-08)
Character-Aware Neural Language Models
1606.05250 (2016-06)
SQuAD: 100,000+ Questions for Machine Comprehension of Text
1608.07905 (2016-08)
Machine Comprehension Using Match-LSTM and Answer Pointer
and 130 more not named here
unpad_dataproto 89 other papers
36 dated earlier, 13 the same month, 37 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 86 more not named here
squeeze 82 other papers
36 dated earlier, 12 the same month, 31 later, 3 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2025.findings-emnlp.1015 (2025 (year only))
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
and 79 more not named here
get_generation_config 63 other papers
22 dated earlier, 10 the same month, 29 later, 2 undated
2409.19256 (2024-09)
HybridFlow: A Flexible and Efficient RLHF Framework
2410.21236 (2024-10)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
2502.19613 (2025-02)
Self-rewarding correction for mathematical reasoning
and 60 more not named here
generate_config_from_args 57 other papers
8 dated earlier, 9 the same month, 37 later, 3 undated
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2510.08630 (2025-10)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
and 54 more not named here
get_dynamic_pipeline_shards 52 other papers
7 dated earlier, 8 the same month, 35 later, 2 undated
2410.02992 (2024-10)
Learning to Better Search with Language Models via Guided Reinforced Self-Training
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2510.08630 (2025-10)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
and 49 more not named here
get_huggingface_actor_config 28 other papers
2 dated earlier, 6 the same month, 19 later, 1 undated
2509.25787 (2025-09)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
2601.02648 (2026-01)
Prioritized Replay for RL Post-training
2602.03048 (2026-02)
CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs
and 25 more not named here
em_check 5 other papers
1 dated earlier, 2 the same month, 2 later
2510.00568 (2025-10)
ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
2602.02258 (2026-02)
Alignment-Aware Model Adaptation via Feedback-Guided Optimization
2602.03645 (2026-02)
Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAG
and 2 more not named here
subem_check 3 other papers
1 the same month, 2 later
2602.02258 (2026-02)
Alignment-Aware Model Adaptation via Feedback-Guided Optimization
2603.11327 (2026-03)
Meta-Reinforcement Learning with Self-Reflection for Agentic Search
2608.01904 (2026-08)
CoEvoKG: Co-Evolving Knowledge Graphs with Self-Evolving Search Agents

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many real-world knowledge sources are organized as heterogeneous graphs rather than plain text. Reasoning over such graphs requires models to follow schema-defined relations through precise function calls and to aggregate evidence across multiple rounds of interaction. We propose GRAPHDANCER, a two-stage post-training framework that teaches LLMs to reason over graphs by interleaving natural-language reasoning with graph function execution. The first stage teaches the model how to interact with the graph under rule-based rewards, while the second stage further teaches it to prefer more grounded and efficient interaction trajectories. The key novelty of GRAPH-DANCER is a graph-aware curriculum that organizes both stages by the structural complexity of information-seeking trajectories, progressively increasing task difficulty during training. We evaluate GRAPHDANCER on a multidomain benchmark by training on one domain only and testing on unseen domains and outof-distribution question types. Despite using only a 3B backbone, GRAPHDANCER outperforms baselines equipped with larger/stronger backbones, demonstrating robust cross-domain generalization of graph exploration and reasoning skills. Our code can be found at https:// github.com/leopoldwhite/GraphDancer.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.02518")
get_code_for_paper("2602.02518")
have("2602.02518")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.02518.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.02518.svg)](https://syntology.ai/paper/2602.02518)

Connect an agent — have() is free.