Yuling

YerbaPage's activity

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

authored a paper 2 days ago

Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?

Paper • 2609.27891 • Published Aug 21 • 16

upvoted a paper 2 days ago

Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?

Paper • 2609.27891 • Published Aug 21 • 16

upvoted a paper 7 days ago

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 12 days ago • 214

authored 2 papers 23 days ago

SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning

Paper • 2608.23493 • Published Aug 24 • 1

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

Paper • 2609.02783 • Published 24 days ago • 62

posted an update 23 days ago

view post

Post

74

You don't have to run an agent evaluation to the end.

An agent's final outcome is usually visible from its early behavior, so we just stop the run once it's clear.

EarlyEval cuts 13% to 26% of steps and up to 44% of input tokens, and resolve rates move by only 1 to 2 points.

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction (2609.02783)
https://github.com/inphotoo/earlyeval

See translation

🔥

1

1

+

Reply

upvoted 2 papers 23 days ago

SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning

Paper • 2608.23493 • Published Aug 24 • 1

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

Paper • 2609.02783 • Published 24 days ago • 62

submitted a paper to Daily Papers 23 days ago

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

Paper • 2609.02783 • Published 24 days ago • 62

upvoted a paper about 1 month ago

CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild

Paper • 2608.23181 • Published Aug 24 • 34

authored a paper about 1 month ago

ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

Paper • 2608.16425 • Published Aug 17 • 40

upvoted a paper about 1 month ago

ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

Paper • 2608.16425 • Published Aug 17 • 40

submitted a paper to Daily Papers about 1 month ago

ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

Paper • 2608.16425 • Published Aug 17 • 40

authored 3 papers about 1 month ago

Repo0: Design-Driven Zero-to-All Code Generation

Paper • 2608.19854 • Published Aug 20 • 22

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Paper • 2608.09802 • Published Aug 10 • 84

Rethinking Code Complexity Through the Lens of Large Language Models

Paper • 2602.07882 • Published May 27

upvoted a paper about 1 month ago

Repo0: Design-Driven Zero-to-All Code Generation

Paper • 2608.19854 • Published Aug 20 • 22

authored a paper about 1 month ago

SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution

Paper • 2608.18933 • Published Aug 19 • 13

upvoted 2 papers about 1 month ago

SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution

Paper • 2608.18933 • Published Aug 19 • 13

Second Thought: Reasoning in Parallel as LLM Agents Act and Observe

Paper • 2608.13667 • Published Aug 13 • 17