LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data

Zhennan Wan; Jianfei Chen

cs.CLOct 21, 2026

LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data

Authors: Zhennan Wan, Jianfei Chen

Organizations: Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University

Abstract

Reinforcement learning (RL) is an effective way to strengthen the long-context reasoning of large language models (LLMs), but it needs training data that are long, diverse, challenging, and verifiable. Human annotation of such data is expensive, naturally occurring data are too scarce to sustain RL, and existing synthesis methods depend on external corpora or stronger teacher models, which become harder to obtain as the trained models get stronger. Recently, RL from zero data, in which a model learns from tasks it proposes itself, has achieved excellent performance, but existing methods target short-context tasks. Therefore, we propose $\textbf{LongZero}$ , a method that lets an LLM improve its own long-context reasoning without any external data. Instead of writing questions and answers over existing documents, LongZero first has the model synthesize the question and answer with its supporting evidence in a compact structured form, and only then separately expands the evidence into a long multi-document context. LongZero combines these self-written multi-hop reasoning tasks with self-written multi-round retrieval tasks and trains the model with GRPO. We evaluate LongZero on two LLMs across five long-context reasoning benchmarks and compare it with RL on data synthesized from external corpora. Experimental results show that LongZero can generalize to real tasks, and outperforms both baselines, suggesting a viable and promising path to improving long-context reasoning of LLMs.

Figures & tables

Figure 1: Core idea of LongZero . (a) Existing methods build long-context RL data from external corpora. (b) LongZero lets the policy write the question, evidence, and answer, expand them into long-context data, and learn with RL from answering its own questions.

Figure 2: Overview of LongZero data generation, with real data synthesized by Qwen3-4B-Thinking-2507. Left: for reasoning data, the policy writes a world specification, plans which document states each fact, and expands the plan into long documents. Right: retrieval data are long conversations assembled from the policy’s own responses.

Synthesis per 2,560 unstable reasoning questions
	Qwen3-4B-T	Qwen3-8B
Worlds attempted	~3.8K	~5.4K
Worlds accepted	~3.6K	~5.1K
Questions filtered	~14.4K	~19.5K
always correct	69.3%	68.3%
unstable (kept)	17.7%	13.1%

Table 1: Data synthesized by each model for itself. Upper: synthesis needed for the 2,560 unstable reasoning questions used, estimated from each model’s rates. Lower: training (validation) data; token counts use each model’s tokenizer. Qwen3-4B-T: Qwen3-4B-Thinking-2507.

7 Method	LB1	LBv2	FRAMES	AA-LCR	LongReason	Avg
Qwen3-4B-Thinking-2507
Base model	65.43	40.56	51.27	36.50	79.66	54.68
Enhanced HotpotQA (from LoongRL)	65.94	43.04	51.46	41.50	80.92	56.57
Teacher-synthesized QA	66.12	41.85	52.97	38.50	80.48	55.99
LongZero (Ours)	67.22	43.34	55.76	39.50	81.30	57.42
Qwen3-8B (Thinking)

Table 2: Results on five long-context reasoning benchmarks (mean of two runs; LongReason: 32K split; Avg: unweighted mean). Best results for each base model are in bold and second-best results are underlined . All methods share the RL configuration and checkpoint step.

Panel of Figure 3 — Figure 3: Training dynamics of LongZero up to the reported checkpoints. Validation scores are measured every 6 steps on held-out reasoning and retrieval data (overall: weighted by set size). The training reward mixes both data types (line: 5-step average; band: range over the same window).

7 Training data	LB1	LBv2	FRAMES	AA-LCR	LongReason	Avg
Base model	65.43	40.56	51.27	36.50	79.66	54.68
Reasoning data only	67.04	42.64	54.61	34.00	78.59	55.38
Retrieval data only	64.51	41.65	52.18	33.00	77.90	53.85
Reasoning and retrieval data, 1:1	67.29	41.35	53.64	36.50	80.98	55.95
Reasoning and retrieval data, 2:1 (Ours)	67.22	43.34	55.76	39.50	81.30	57.42

Table 3: Ablation on the training data of Qwen3-4B-Thinking-2507: reasoning data only, retrieval data only, and mixtures of the two in a 1:1 and a 2:1 ratio. All runs share the RL configuration. Best results are in bold and second-best results are underlined .

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Stage	Decoding	Max tokens
Specification	thinking, $T{=}0.7$ / $0.6$	28,672
Plan	$T{=}0.8$ (non-thinking † )	16,384
Expansion	$T{=}0.8$ (non-thinking † )	5,120
Difficulty filter	thinking, $T{=}0.7$	8,192

Appendix

Table 4: Generation settings for reasoning data, all with top-

p

0.95.

T{=}0.7

applies to Qwen3-4B-Thinking-2507, which always thinks, and

T{=}0.6

to Qwen3-8B with thinking. † Qwen3-8B only.

Hyperparameter	Value
Algorithm	GRPO (verl)
Batch per step	64 prompts $\times$ 8
Training steps	72 (4B), 108 (8B)
PPO update	16 prompts, 1 epoch
Optimizer	AdamW (0.9, 0.999)
Learning rate	$10^{-6}$ , constant

Appendix

Table 5: RL hyperparameters shared by all methods.

5 Method	HQA	2WQA	MSQ	Avg
Base model	67.04	78.46	50.79	65.43
Enhanced HotpotQA	66.59	76.41	54.82	65.94
Teacher-synthesized QA	67.73	77.97	52.68	66.12
LongZero (Ours)	67.17	79.62	54.86	67.22

Appendix

Table 6: LB1 F1 of Qwen3-4B-Thinking-2507 on each of its three datasets. Avg is the LB1 score in Table 2 .

5 Method	HQA	2WQA	MSQ	Avg
Base model	66.58	76.83	47.48	63.63
Enhanced HotpotQA	67.91	75.43	51.60	64.98
Teacher-synthesized QA	66.99	76.12	49.08	64.07
LongZero (Ours)	66.90	78.20	51.38	65.49

Appendix

Table 7: LB1 F1 of Qwen3-8B on each of its three datasets, which contain 200 questions each. Avg is the LB1 score in Table 2 .

7 \Block 2-1 Method	Difficulty		Length			\Block 2-1 Overall
	Easy	Hard	Short	Medium	Long
Base model	48.44	35.69	47.78	37.44	34.72	40.56
\Block [l]Enhanced
HotpotQA	49.74	38.91	51.67	38.37	37.96	43.04
\Block [l]Teacher-
synthesized QA	47.66	38.26	51.94	35.12	38.43	41.85

Appendix

Table 8: LBv2 accuracy of Qwen3-4B-Thinking-2507 by difficulty and by input length, using the labels provided with LBv2. Overall is the LBv2 score in Table 2 .

7 \Block 2-1 Method	Difficulty		Length			\Block 2-1 Overall
	Easy	Hard	Short	Medium	Long
Base model	40.89	26.69	45.00	25.35	24.07	32.11
\Block [l]Enhanced
HotpotQA	37.24	27.65	44.17	23.49	25.46	31.31
\Block [l]Teacher-
synthesized QA	38.54	29.90	45.83	27.21	24.07	33.20

Appendix

Table 9: LBv2 accuracy of Qwen3-8B by difficulty and by input length, using the labels provided with LBv2. Overall is the LBv2 score in Table 2 .

5 Training data	HQA	2WQA	MSQ	Avg
Base model	67.04	78.46	50.79	65.43
Reasoning data only	68.51	78.45	54.15	67.04
Retrieval data only	64.57	78.48	50.48	64.51
\Block [l]Reasoning and
retrieval data, 1:1	67.33	79.58	54.96	67.29
\Block [l]Reasoning and retrieval

Appendix

Table 10: LB1 F1 of the ablation variants of Qwen3-4B-Thinking-2507 on each dataset. Avg is the LB1 score in Table 3 .

data	Difficulty		Length			\Block 2-1 Overall
7 \Block 2-1 Training
	Easy	Hard	Short	Medium	Long
\Block [l]Base
model	48.44	35.69	47.78	37.44	34.72	40.56
\Block [l]Reasoning
data only	51.04	37.46	48.33	39.77	38.89	42.64

Appendix

Table 11: LBv2 accuracy of the ablation variants of Qwen3-4B-Thinking-2507 by difficulty and by input length. Overall is the LBv2 score in Table 3 .

Long-Context Reasoning in Language Models

See all 43 papers

A Decomposition Perspective to Long-context Reasoning for LLMs
Apr 9, 2026Yanling Xiao, Huaibing Xie, Guoliang Zhao +8Long-Context Reasoning in Language Models
Large Language Model Department, Tencent · Xi’an Jiaotong University, Xi’an, China · Fudan University, Shanghai, China +2
Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
Jun 17, 2026Xiaoyue Xu, Sikui Zhang, Xiaorong Wang +2Training Data Curation RL for Language Model Reasoning
OpenBMB · Tsinghua University
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Jul 2, 2026Yanjun Zhao, Ruizhong Qiu, Tianxin Wei +6Long-Context Inference Long-Context Reasoning in Language Models
University of Illinois Urbana-Champaign

Apr 9, 2026J/K move · Enter open · S save

A Decomposition Perspective to Long-context Reasoning for LLMs

Yanling Xiao, Huaibing Xie, Guoliang Zhao, Shihan Dou+7

Large Language Model Department, Tencent · Xi’an Jiaotong University, Xi’an, China · Fudan University, Shanghai, China+2

Long-Context Reasoning in Language Models

Open paper AskPDF arXiv

Long-context reasoning is essential for complex real-world applications, yet remains a significant challenge for Large Language Models (LLMs). Despite the rapid evolution in long-context reasoning, current research often overlooks the internal complexity of the long-context reasoning task itself. In this paper, we move beyond this holistic view and decompose long-context reasoning into a set of fundamental atomic skills, and we then automatically synthesize a suite of pseudo datasets, each explicitly targeting a specific atomic skill. Our empirical analysis confirms that proficiency in these atomic skills is strongly correlated with general long-text reasoning performance. Building on this insight, we employ reinforcement learning on these pseudo datasets to sharpen the model's atomic skills, in the hope of boosting its general long-context reasoning ability. Extensive experiments across multiple benchmarks demonstrate the effectiveness of our approach: it outperforms a strong baseline by an average margin of 7.7% (improving from 46.3% to 54.0%) across Loogle, Loong, LongBench-v2, BrowscompLong, Ruler-qa2, and MRCR.

Abstract

Long-Context Reasoning in Language Models

Explore similar work

A Decomposition Perspective to Long-context Reasoning for LLMs

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning