Salesforce AI Research

company

Verified

https://www.salesforceairesearch.com/

AI & ML interests

None defined yet.

Recent Activity

Taksu updated a Space 2 days ago

Salesforce/GIFT-Eval

yli-ml submitted a paper 10 days ago

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

ZixuanKe submitted a paper 24 days ago

EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?

View all activity

Papers

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training

View all Papers

updated a Space 2 days ago

GIFT Eval

GIFT-Eval: A Benchmark for General Time Series Forecasting

submitted a paper to Daily Papers 10 days ago

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Paper • 2609.27334 • Published 11 days ago • 56

submitted a paper to Daily Papers 24 days ago

EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?

Paper • 2609.04280 • Published Sep 3 • 32

submitted a paper to Daily Papers 27 days ago

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Paper • 2609.05295 • Published about 1 month ago • 19

submitted a paper to Daily Papers about 1 month ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published Sep 3 • 188

updated a dataset about 1 month ago

Salesforce/tracelab-comprehend

Updated Sep 2 • 131

published a dataset about 1 month ago

Salesforce/tracelab-comprehend

Updated Sep 2 • 131

updated a dataset about 2 months ago

Salesforce/self-improve-fragility

Viewer • Updated Aug 18 • 39.3k • 4k

submitted a paper to Daily Papers about 2 months ago

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published Jul 31 • 116

published a dataset about 2 months ago

Salesforce/self-improve-fragility

Viewer • Updated Aug 18 • 39.3k • 4k

submitted a paper to Daily Papers 2 months ago

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

Paper • 2607.22798 • Published Jul 24 • 63

updated a dataset 2 months ago

Salesforce/lalm-judge-validation-full-duplex

Viewer • Updated Jul 23 • 1.97k • 74 • 2

submitted a paper to Daily Papers 3 months ago

Evidence-Backed Video Question Answering

Paper • 2607.11862 • Published Jul 13 • 5

published a model 3 months ago

Salesforce/RetailSim-GRPO-4B

Updated Jun 22 • 18 • 1

published a dataset 3 months ago

Salesforce/lalm-judge-validation-full-duplex

Viewer • Updated Jul 23 • 1.97k • 74 • 2

updated a model 3 months ago

Salesforce/RetailSim-GRPO-4B

Updated Jun 22 • 18 • 1

updated a dataset 4 months ago

Salesforce/MASBench

Viewer • Updated Jun 11 • 40.5k • 148 • 3

updated a dataset 4 months ago

Salesforce/ST-Evidence-Bench

Preview • Updated Jun 1 • 256

submitted a paper to Daily Papers 5 months ago

Learning from Language Feedback via Variational Policy Distillation

Paper • 2605.15113 • Published May 18 • 13

published a dataset 5 months ago

Salesforce/MTA-Vision-DeepSearch

Viewer • Updated May 19 • 178 • 950