StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
Paper • 2607.22798 • Published • 55
AI & ML interests
Omni Lingual Models
Recent Activity
View all activity
Ziyang
authored a
paper 1 day ago
Ziyang
submitted a
paper to Daily Papers 2 days ago
ajibawa-2023
posted an update 12 days ago
Post
3526
Technical-Architectures-Large
Dataset: ajibawa-2023/Technical-Architectures-Large
This dataset provides over 210,000 distinct enterprise software architectures generated using two open source models: GPT-OSS-120B and Qwen3-Coder-Next-FP8.
These architectures model realistic enterprise systems complete with client layers, edge security, API gateways, service meshes, compliance boundaries, and multi-cloud infrastructure topologies.
Dataset: ajibawa-2023/Technical-Architectures-Large
This dataset provides over 210,000 distinct enterprise software architectures generated using two open source models: GPT-OSS-120B and Qwen3-Coder-Next-FP8.
These architectures model realistic enterprise systems complete with client layers, edge security, API gateways, service meshes, compliance boundaries, and multi-cloud infrastructure topologies.
Chaning License to ODC-By
1
#2 opened 20 days ago
by 
huu-ontocord
Chaning License to ODC-By
1
#2 opened 20 days ago
by huu-ontocord
huu-ontocord
updated a
dataset 20 days ago
felfri
authored a
paper 29 days ago
PSaiml
authored a
paper 29 days ago
ajibawa-2023
posted an update about 1 month ago
Post
6934
Shell-Code-Large
Dataset: ajibawa-2023/Shell-Code-Large
Shell-Code-Large is a large-scale corpus of Shell scripting source code comprising approximately 640,000 code samples stored in JSON Lines (.jsonl) format. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, DevOps automation, cloud infrastructure engineering, system administration, and software engineering automation.
By providing a high-volume, language-specific corpus focused exclusively on Shell scripting, Shell-Code-Large enables systematic experimentation in automation workflows, deployment pipelines, infrastructure management, and command-line tooling. These domains remain foundational to Linux systems, cloud-native platforms, CI/CD environments, and modern DevOps practices.
Shell-Code-Large addresses the need for a dedicated Shell-focused dataset at substantial scale, enabling targeted research into scripting patterns, command composition, workflow orchestration, infrastructure automation, and operational engineering practices
Dataset: ajibawa-2023/Shell-Code-Large
Shell-Code-Large is a large-scale corpus of Shell scripting source code comprising approximately 640,000 code samples stored in JSON Lines (.jsonl) format. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, DevOps automation, cloud infrastructure engineering, system administration, and software engineering automation.
By providing a high-volume, language-specific corpus focused exclusively on Shell scripting, Shell-Code-Large enables systematic experimentation in automation workflows, deployment pipelines, infrastructure management, and command-line tooling. These domains remain foundational to Linux systems, cloud-native platforms, CI/CD environments, and modern DevOps practices.
Shell-Code-Large addresses the need for a dedicated Shell-focused dataset at substantial scale, enabling targeted research into scripting patterns, command composition, workflow orchestration, infrastructure automation, and operational engineering practices
felfri
authored 3
papers about 1 month ago
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
Paper • 2604.15149 • Published • 2
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting
Paper • 2606.09809 • Published • 4
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
Paper • 2606.19162 • Published • 21
Locutusque
posted an update 2 months ago
Post
402
🚀 Introducing Esmeralda-Llama-3.1-8B-control
The first release in the Esmeralda model family by Locutusque.
This model is intentionally small and experimental — a control/baseline proof-of-concept designed to answer one question:
«“How strong is my new "Locutusque/esmeralda-agentic" dataset before scaling to larger runs?”»
Training Details
- Base: Llama 3.1 8B
- Training precision: bf16 mixed precision
- Chat template: modified ChatML
- Dataset size: ~37k examples
- Examples actually used for this run: ~5k
The dataset includes:
- multi-turn agentic traces
- reasoning traces
- structured assistant behavior
- generalist instruction data
Benchmark Results
Compared against:
- Llama 3.1 8B Instruct
- Hermes-3-Llama-3.1-8B
HumanEval
57.3 — Esmeralda
56.1 — Llama 3.1 Instruct
52.4 — Hermes-3
MBPP
53.2 — Esmeralda
56.8 — Llama 3.1 Instruct
48.2 — Hermes-3
GPQA Diamond
15.7 — Esmeralda
15.7 — Llama 3.1 Instruct
18.2 — Hermes-3
EQ-Bench
59.2 — Esmeralda
61.1 — Llama 3.1 Instruct
63.1 — Hermes-3
EQ-Bench Parseable (Syntax Stability)
🔥 100.0% — Esmeralda
92.4% — Llama 3.1 Instruct
91.2% — Hermes-3
Here Be Dragons 🐉
I also experimented with a new TruthfulQA free-generation evaluation setup.
- Responses were judged by Gemma 4 26B A4B
- The judge compared generations directly against ground-truth answers
- Models were evaluated in 8-bit quantized form to speed up inference
TruthfulQA (LLM Judge)
0.682 — Esmeralda-Llama-3.1-8B-control
0.587 — Hermes-3-Llama-3.1-8B (reported MC2 score; methodology differs)
For a lightweight control run trained on only a fraction of the dataset, I’m pretty encouraged by the results.
The model is released under the standard Llama 3.1 license, and I’d genuinely love feedback from people testing it in real workflows.
Model: Locutusque/Esmeralda-Llama-3.1-8B-control
Dataset: Locutusque/esmeralda-agentic
The first release in the Esmeralda model family by Locutusque.
This model is intentionally small and experimental — a control/baseline proof-of-concept designed to answer one question:
«“How strong is my new "Locutusque/esmeralda-agentic" dataset before scaling to larger runs?”»
Training Details
- Base: Llama 3.1 8B
- Training precision: bf16 mixed precision
- Chat template: modified ChatML
- Dataset size: ~37k examples
- Examples actually used for this run: ~5k
The dataset includes:
- multi-turn agentic traces
- reasoning traces
- structured assistant behavior
- generalist instruction data
Benchmark Results
Compared against:
- Llama 3.1 8B Instruct
- Hermes-3-Llama-3.1-8B
HumanEval
57.3 — Esmeralda
56.1 — Llama 3.1 Instruct
52.4 — Hermes-3
MBPP
53.2 — Esmeralda
56.8 — Llama 3.1 Instruct
48.2 — Hermes-3
GPQA Diamond
15.7 — Esmeralda
15.7 — Llama 3.1 Instruct
18.2 — Hermes-3
EQ-Bench
59.2 — Esmeralda
61.1 — Llama 3.1 Instruct
63.1 — Hermes-3
EQ-Bench Parseable (Syntax Stability)
🔥 100.0% — Esmeralda
92.4% — Llama 3.1 Instruct
91.2% — Hermes-3
Here Be Dragons 🐉
I also experimented with a new TruthfulQA free-generation evaluation setup.
- Responses were judged by Gemma 4 26B A4B
- The judge compared generations directly against ground-truth answers
- Models were evaluated in 8-bit quantized form to speed up inference
TruthfulQA (LLM Judge)
0.682 — Esmeralda-Llama-3.1-8B-control
0.587 — Hermes-3-Llama-3.1-8B (reported MC2 score; methodology differs)
For a lightweight control run trained on only a fraction of the dataset, I’m pretty encouraged by the results.
The model is released under the standard Llama 3.1 license, and I’d genuinely love feedback from people testing it in real workflows.
Model: Locutusque/Esmeralda-Llama-3.1-8B-control
Dataset: Locutusque/esmeralda-agentic
chiennv
authored 3
papers 3 months ago
Lizard: An Efficient Linearization Framework for Large Language Models
Paper • 2507.09025 • Published • 19
InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Paper • 2603.03646 • Published • 8
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
Paper • 2605.12825 • Published • 13
chiennv
submitted a
paper to Daily Papers 3 months ago
ajibawa-2023
posted an update 3 months ago
Post
2232
Stitched-Reasoning-Trajectories-7M
Dataset: ajibawa-2023/Stitched-Reasoning-Trajectories-7M
Stitched-Reasoning-Trajectories-7M is a massive-scale, synthetic multi-hop reasoning dataset. It was built by algorithmically "stitching" together discrete reasoning traces from the original glaiveai/reasoning-v1-20m dataset into continuous, coherent, and logically structured multi-agent trajectories.
By extracting internal sub-questions from <think> blocks and mapping high-information keyword overlaps, this dataset transforms single-turn Q&A pairs into deep, multi-step research plans. To ensure high quality and eliminate "topic drift," every trajectory has been verified using a dense semantic embedding model (BAAI/bge-large-en-v1.5).
The resulting dataset consists of 709 .jsonl files containing over 7.2 million entirely deduplicated, highly coherent reasoning chains.
Dataset: ajibawa-2023/Stitched-Reasoning-Trajectories-7M
Stitched-Reasoning-Trajectories-7M is a massive-scale, synthetic multi-hop reasoning dataset. It was built by algorithmically "stitching" together discrete reasoning traces from the original glaiveai/reasoning-v1-20m dataset into continuous, coherent, and logically structured multi-agent trajectories.
By extracting internal sub-questions from <think> blocks and mapping high-information keyword overlaps, this dataset transforms single-turn Q&A pairs into deep, multi-step research plans. To ensure high quality and eliminate "topic drift," every trajectory has been verified using a dense semantic embedding model (BAAI/bge-large-en-v1.5).
The resulting dataset consists of 709 .jsonl files containing over 7.2 million entirely deduplicated, highly coherent reasoning chains.
felfri
authored a
paper 3 months ago
huu-ontocord
authored a
paper 3 months ago