SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
Paper โข 2604.17308 โข Published โข 22
ZeroGPU Explorers
community
AI & ML interests
None defined yet.
Recent Activity
Lin-Chenย
authored 4
papers 7 days ago
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
Paper โข 2605.16079 โข Published โข 28
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
Paper โข 2605.17526 โข Published โข 7
AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios
Paper โข 2605.27995 โข Published โข 16
Locutusqueย
posted an update 10 days ago
Post
235
๐ Introducing Esmeralda-Llama-3.1-8B-control
The first release in the Esmeralda model family by Locutusque.
This model is intentionally small and experimental โ a control/baseline proof-of-concept designed to answer one question:
ยซโHow strong is my new "Locutusque/esmeralda-agentic" dataset before scaling to larger runs?โยป
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 โ Esmeralda
56.1 โ Llama 3.1 Instruct
52.4 โ Hermes-3
MBPP
53.2 โ Esmeralda
56.8 โ Llama 3.1 Instruct
48.2 โ Hermes-3
GPQA Diamond
15.7 โ Esmeralda
15.7 โ Llama 3.1 Instruct
18.2 โ Hermes-3
EQ-Bench
59.2 โ Esmeralda
61.1 โ Llama 3.1 Instruct
63.1 โ Hermes-3
EQ-Bench Parseable (Syntax Stability)
๐ฅ 100.0% โ Esmeralda
92.4% โ Llama 3.1 Instruct
91.2% โ Hermes-3
Here Be Dragons ๐
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 โ Esmeralda-Llama-3.1-8B-control
0.587 โ Hermes-3-Llama-3.1-8B (reported MC2 score; methodology differs)
For a lightweight control run trained on only a fraction of the dataset, Iโm pretty encouraged by the results.
The model is released under the standard Llama 3.1 license, and Iโd 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 โ a control/baseline proof-of-concept designed to answer one question:
ยซโHow strong is my new "Locutusque/esmeralda-agentic" dataset before scaling to larger runs?โยป
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 โ Esmeralda
56.1 โ Llama 3.1 Instruct
52.4 โ Hermes-3
MBPP
53.2 โ Esmeralda
56.8 โ Llama 3.1 Instruct
48.2 โ Hermes-3
GPQA Diamond
15.7 โ Esmeralda
15.7 โ Llama 3.1 Instruct
18.2 โ Hermes-3
EQ-Bench
59.2 โ Esmeralda
61.1 โ Llama 3.1 Instruct
63.1 โ Hermes-3
EQ-Bench Parseable (Syntax Stability)
๐ฅ 100.0% โ Esmeralda
92.4% โ Llama 3.1 Instruct
91.2% โ Hermes-3
Here Be Dragons ๐
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 โ Esmeralda-Llama-3.1-8B-control
0.587 โ Hermes-3-Llama-3.1-8B (reported MC2 score; methodology differs)
For a lightweight control run trained on only a fraction of the dataset, Iโm pretty encouraged by the results.
The model is released under the standard Llama 3.1 license, and Iโd genuinely love feedback from people testing it in real workflows.
Model: Locutusque/Esmeralda-Llama-3.1-8B-control
Dataset: Locutusque/esmeralda-agentic
Lin-Chenย
authored a
paper 14 days ago
Post
2822
๐๐ปโโ๏ธ Hey there folks ,
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
- 2 replies
Post
2619
I'm releasing OpenCS2 a 11TB dataset of around 5000 hours of counter strike gameplay recording.
- HD resolution - 1280ร720 ยท 32 fps
- For each frame keyboard and mouse + world state (player position, velocity, weapon ...)
- HD Stereo audio
- All 10 players perspective
https://huggingface.co/collections/blanchon/opencs2
- HD resolution - 1280ร720 ยท 32 fps
- For each frame keyboard and mouse + world state (player position, velocity, weapon ...)
- HD Stereo audio
- All 10 players perspective
https://huggingface.co/collections/blanchon/opencs2
- 1 reply
Lin-Chenย
authored 3
papers 23 days ago
VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
Paper โข 2602.12735 โข Published โข 8
Flow-OPD: On-Policy Distillation for Flow Matching Models
Paper โข 2605.08063 โข Published โข 100
SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
Paper โข 2605.08043 โข Published โข 10
Aurelien-Morganย
posted an update about 1 month ago
Post
1086
@retrain-pipelines v0.2.0 is out !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
- 1 reply
wren93ย
authored a
paper about 1 month ago
Post
4296
๐๐ปโโ๏ธ Hey there folks,
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
- 2 replies
Post
3643
๐๐ปโโ๏ธ Hey there folks ,
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
Q-bertย
authored a
paper about 1 month ago
Why doesn't anyone host llms in zerogpu spaces?
8
#172 opened about 2 months ago
by 
Reality123b
Why doesn't anyone host llms in zerogpu spaces?
8
#172 opened about 2 months ago
by Reality123b
Aurelien-Morganย
posted an update about 2 months ago
wren93ย
authored a
paper about 2 months ago