Bhavishya Pohani

bhavishya2895's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 4 days ago

snorkelai/r4m-30b-a3b

Updated 4 days ago

published a model 4 days ago

snorkelai/r4m-30b-a3b

Updated 4 days ago

upvoted a paper about 1 month ago

SkillOrchestra: Learning to Route Agents via Skill Transfer

Paper • 2602.19672 • Published Feb 23 • 57

updated a Space about 1 month ago

Running on CPU Upgrade

RL

FinQA Environment Server

🔊

Control and monitor an interactive environment via web UI

published a Space about 1 month ago

Running on CPU Upgrade

RL

FinQA Environment Server

🔊

Control and monitor an interactive environment via web UI

New activity in snorkelai/finqa-data about 1 month ago

Standardize percentage and rate GT labels to decimal ratios

#4 opened about 1 month ago by

bhavishya2895

Standardize percentage GT labels to decimal ratios Converted 13 ground truth labels from raw percentages/percentage points to decimal ratios for consistency with the system prompt instruction to always express percentages as ratios (divide by 100). Examples: -7.290 -> -0.0729, 6.000 -> 0.06, 50.000 -> 0.5

#3 opened about 1 month ago by

bhavishya2895

New activity in snorkelai/agent-finance-reasoning about 1 month ago

Standardize percentage GT labels to decimal ratios

#3 opened about 1 month ago by

bhavishya2895

New activity in snorkelai/finqa-data about 1 month ago

Standardize GT answer formats

1

#2 opened about 1 month ago by

bhavishya2895

updated a dataset about 2 months ago

snorkelai/finqa-data

Viewer • Updated Feb 17 • 290 • 2.34k • 1

published a dataset 2 months ago

snorkelai/finqa-data

Viewer • Updated Feb 17 • 290 • 2.34k • 1

upvoted an article 4 months ago

view article

Article

Building the Open Agent Ecosystem Together: Introducing OpenEnv

• 
• 
• +8

Oct 23, 2025

•

154

liked a dataset 4 months ago

snorkelai/Tau2-Bench-Airline-With-Code-Agents

Viewer • Updated Dec 3, 2025 • 500 • 162 • 8

New activity in meta-agents-research-environments/leaderboard 5 months ago

Open source traces

2

#2 opened 5 months ago by

bhavishya2895

upvoted a paper 5 months ago

Automating Benchmark Design

Paper • 2510.25039 • Published Oct 28, 2025 • 16

liked 2 datasets 5 months ago

snorkelai/Multi-Turn-Insurance-Underwriting-Code-Gen

Viewer • Updated Oct 23, 2025 • 1.8k • 92 • 4

meta-agents-research-environments/gaia2

Viewer • Updated Sep 25, 2025 • 963 • 28.6k • 38

upvoted an article 6 months ago

view article

Article

CodeAgents + Structure: A Better Way to Execute Actions

• 
• 

May 28, 2025

•

82

liked a dataset 6 months ago

arvindh75/Long-Horizon-Execution

Viewer • Updated Sep 16, 2025 • 100 • 150 • 14

upvoted a paper 6 months ago

Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction

Paper • 2407.03651 • Published Jul 4, 2024 • 17