Good Papers

Showing papers from Salesforce (United States) Show all papers

72%Highly rated
?Highly ratedVote to see the score
arXivSalesforceLLM agents & planning

Agentic Uncertainty Quantification

A dual-process agentic framework converts verbalized uncertainty into active control signals to prevent error propagation and improve trajectory calibration without training.

Jiaxin Zhang, Prafulla Kumar Choubey, Kung-Hsiang Huang, Caiming Xiong and 1 more

Published Jan 22, 2026 · 0 citations · ▲ 9 on Hugging Face

– ReadersNo votes yet
8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 8 of 20 reviewers recommend it
lenient 4/5
medium 4/10
strict 0/5
80%Must read
?Must readVote to see the score
arXivU Illinois Urbana-ChampaignSalesforceRL for LLMs

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning

xRouter trains a reinforcement learning router that either answers directly or calls external models using a cost-aware reward, reducing costs while maintaining task completion rates.

Qian, Cheng, Zuxin Liu, Shirley Kokane, Akshara Prabhakar and 9 more

Published Oct 9, 2025 · 0 citations · ▲ 1 on Hugging Face

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5