Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised research loops that drive real AI progress. We present ASI-Evolve, an agentic framework for AI-for-AI research that closes this loop through a learn-design-experiment-analyze cycle. ASI-Evolve augments standard evolutionary agents with two key components: a cognition base that injects accumulated human priors into each round of exploration, and a dedicated analyzer that distills complex experimental outcomes into reusable insights for future iterations. To our knowledge, ASI-Evolve is the first unified framework to demonstrate AI-driven discovery across three central components of AI development: data, architectures, and learning algorithms. In neural architecture design, it discovered 105 SOTA linear attention architectures, with the best discovered model surpassing DeltaNet by +0.97 points, nearly 3x the gain of recent human-designed improvements. In pretraining data curation, the evolved pipeline improves average benchmark performance by +3.96 points, with gains exceeding 18 points on MMLU. In reinforcement learning algorithm design, discovered algorithms outperform GRPO by up to +12.5 points on AMC32, +11.67 points on AIME24, and +5.04 points on OlympiadBench. We further provide initial evidence that this AI-for-AI paradigm can transfer beyond the AI stack through experiments in mathematics and biomedicine. Together, these results suggest that ASI-Evolve represents a promising step toward enabling AI to accelerate AI across the foundational stages of development, offering early evidence for the feasibility of closed-loop AI research.
Figures & tables
Figure 1
Figure 1: Representative scientific automation settings in the Ltask=⟨Cexec,Sspace,Dfeedback⟩ space.
Figure 2: Asi-Evolve pipeline: in each round, the system samples context nodes from database, retrieves relevant cognition items via embedding search, generates a new candidate program, runs an experiment-specific evaluation script under timeouts, and summarizes results into an analysis report that is stored back into the database for future rounds.
Human Discovered
AI Discovered
Benchmarks
DeltaNet
Gated- DeltaNet
Mamba2
PG
C
FG
H
AM
Development
Wiki ppl ↓
17.00
16.84
16.66
16.18
16.05
15.77
16.65
16.26
LMB ppl ↓
13.63
13.31
13.33
12.62
13.45
12.34
13.06
13.75
LMB
45.47
46.26
46.24
47.60
46.13
47.53
46.56
45.04
PIQA
73.12
74.10
73.78
72.91
74.37
72.91
74.37
74.10
Table 1: Top block: 10 development benchmarks, used in our exploration stage; middle block: 6 generalization benchmarks for out-of-distribution testing. Bold indicates the best result and underline is the suboptimal one. Model abbreviations are as follows: PG = PathGate-FusionNet, C = Content-SharpRouter, FG = FusionGated-FIRNet, H = Hier-GateNet, and AM = AdaMulti-PathGateNet.
Human Discovered
AI Discovered
Benchmark
Fineweb-Edu
Ultra-Fineweb
DCLM
Nemotron-CC
Nemotron-CCASI
Nemotron-CCASI+
BBH
3.01
7.42
24.16
26.82
26.69
26.16
ARC-E
73.39
73.96
75.13
74.94
77.55
78.59
ARC-C
43.45
43.77
45.02
43.52
48.41
49.32
MMLU
28.38
25.53
28.54
27.49
32.55
46.13
AGIEval
16.96
17.72
17.90
18.15
18.30
18.21
Table 2: Benchmark comparison of models trained on different pretraining corpora and curation strategies. All models are 3B parameters trained on 500B tokens. Columns are grouped into Human baselines and ASI-Evolve discovered datasets.
Method
Math500
AMC32
AIME25
AIME24
OlympiadBench
GRPO Human
82.0
67.5
20.00
20.00
45.92
Algorithm1 ASI-Evolve
85.6
80.0
29.58
31.67
50.96
Algorithm2 ASI-Evolve
84.6
77.5
23.75
23.33
48.74
Algorithm3 ASI-Evolve
84.8
77.5
30.00
30.00
49.18
Algorithm4 ASI-Evolve
82.4
75.0
20.00
20.00
46.81
Algorithm5 ASI-Evolve
82.0
72.5
23.33
20.00
45.62
Table 3: Performance comparison of evolved RL algorithms and the GRPO baseline on mathematical reasoning benchmarks. All methods were trained on Qwen-3-14B-base within the SIIRL framework using the Skywork OR1 dataset and evaluated after 250 training steps.
Framework
Model
Rounds
Best Score
AlphaEvolve ( Novikov et al., 2025 )
Gemini 2.0 Flash + Claude 3.7
—
2.6359
OpenEvolve ( Sharma, 2025 )
Gemini 2.0 Flash + Claude 3.7
460
2.6343
LoongFlow ( Team, 2024 )
DeepSeek-R1-250528
—
2.6360
SkyDiscover
GPT-5
89
2.6360
ASI-Evolve (Ours)
GPT-5-mini
17
2.6360
Table 4: Circle packing comparison across evolutionary frameworks (26 circles in a 1×1 unit square; higher sum of radii is better). “Rounds” denotes the number of evolution steps to reach the reported best score; “—” indicates the value was not reported.
Figure 3: Comparison experiments. (a) Evolution curves for ASI-Evolve, GEPA, and OpenEvolve. (b) Evolution curves for ASI-Evolve using GPT-5-mini and Qwen3-32B. Shaded regions indicate variability across repeated runs.
Figure 4: Sampling algorithm comparison. Evolution curves for ASI-Evolve with MAP-Elites, UCB1, and Random sampling on Qwen3-32B. Shaded regions show run-to-run variability.
Figure 5: Ablation on circle packing. Evolution curves for the full method and ablated variants. Shaded regions indicate variability across repeated runs.
BindingDB-Dev
BindingDB-Random
Human
BioSNAP
Discovered by
Model
AUROC
F1
AUROC
F1
AUROC
F1
AUROC
F1
Human
TransformerCPI
-
-
93.96
87.02
96.03
91.35
86.35
78.53
PSICHIC
-
-
91.67
83.30
98.55
94.85
91.64
84.87
ConPlex
-
-
93.59
83.39
97.04
90.38
88.40
72.86
ColdStartCPI
-
-
89.27
85.27
98.29
93.57
93.39
86.84
DrugBAN
94.15
86.89
94.89
87.96
98.61
95.40
89.43
82.69
Table 5: Performance comparison on drug-target interaction prediction across multiple benchmarks. We report AUROC (%) and F1 (%) scores for key evaluation settings. Bold indicates best performance.
Unseen Drug
Unseen Protein
Unseen Drug and Protein
Discovered by
Model
AUROC
F1
AUROC
F1
AUROC
F1
Human
DrugBAN
79.15
77.39
82.26
75.76
76.47
71.53
AI
Ours
86.09
82.35
85.82
78.44
80.83
74.51
Table 6: Cold-start performance comparison. We report AUROC (%) and F1 (%) scores. Models must predict interactions for unseen drugs, proteins, or both.
Autonomous research agents use language models and tools to search literature, design and run experiments, analyze results, and support scientific discovery.
Recent progress in LLM agents has advanced the prospect of autonomous research. Yet whether AI can complete difficult long-horizon tasks, especially those that advance AI research itself, remains largely unexplored. We present ASI-Arch, a system for AI-driven AI research that autonomously conducts neural architecture research through a closed-loop research-experiment-analyze-update process. Applied to linear attention, ASI-Arch ran 1,773 iterative experiments and discovered 105 state-of-the-art architectures. Its best architecture improves over DeltaNet by nearly three times the gain achieved by Mamba2. Beyond the final performance gains, we analyze the contributions of different parts of the framework in this hard research setting, shedding light on what enables autonomous progress in complex AI research tasks.
Evolutionary coding agents such as AlphaEvolve are one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scientific problems by iteratively improving and evolving programs, leveraging the prior knowledge and reasoning capabilities of LLMs. Despite their success, mutations over programs are mostly low-level upon surface heuristics, without a persistent unit of control. In contrast, science compounds through ideas. In this work, we propose ExpEvolve, which injects idea-level extraction and control into evolution: it discovers and leverages the high-level factors from programs that explain scoring differences among different programs. We characterize theoretical conditions on when discovery with idea factors improves sample efficiency. We also build a practical framework to show that the extracted high-level idea factors are helpful for guiding exploitation from experience and exploration when discovery comes to a plateau. Across 11 open-ended mathematical tasks, ExpEvolve significantly improves the final performance and sample efficiency up to 5.0x. The improvements also transfer to 4 other LLMs and to 6 machine learning tasks from MLS-Bench. Analysis shows that ExpEvolve can discover idea-level factors to provide better exploration and exploitation for evolutionary discovery.
Yongqiang Chen, Chenxi Liu, Deyu Zou +4
MBZUAI · Carnegie Mellon University · TMLR Group, Hong Kong Baptist University +2
Agent evolvers automate the design of the prompts, skills and workflows around language model agents, yet the optimization process they follow is still designed by hand: a fixed search loop decides how candidates are evaluated, which are kept and when the search stops. We propose FREEEVOLVE, which automates this process as well. An environment specifies the goal, target agent, evaluator, data and resource limits; within these limits, the evolver itself decides what to test, how much evidence to collect, which candidates to pursue and when to stop. These decisions follow an editable evolution skill, which we improve through meta-evolution by scoring each candidate skill on the fresh target agent it produces. The optimization process thus becomes a capability learned from experience rather than a loop engineered in advance. On tau3-bench, ARC-AGI-2, ARC-AGI-3 and Terminal-Bench 2.1, FREEEVOLVE controls the evolution campaign by itself, yet improves the primary held-out metric by 13.6 points on average and matches or exceeds hand-designed evolvers. The learned process keeps improving with experience: meta-evolved skills add 6.9 points over the seed skill on fresh target agents, demonstrating transferability across environments.