ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Paper • 2609.14857 • Published • 172
🏝️ On Vacation
Yuling
YerbaPage
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement authored a paper 16 days ago
SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning authored a paper 16 days ago
EarlyEval: Cheaper Agent Evaluation via Early Outcome PredictionOrganizations
upvoted a paper about 14 hours ago
authored 2
papers 16 days ago
posted an update 16 days ago
Post
73
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
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
upvoted 2
papers 16 days ago
submitted a
paper to Daily Papers 16 days ago
upvoted a paper 24 days ago
authored a
paper 26 days ago
upvoted a paper 26 days ago
submitted a
paper to Daily Papers 26 days ago
authored 3
papers 29 days ago
Repo0: Design-Driven Zero-to-All Code Generation
Paper • 2608.19854 • Published • 22
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Paper • 2608.09802 • Published • 83
Rethinking Code Complexity Through the Lens of Large Language Models
Paper • 2602.07882 • Published
upvoted a paper 29 days ago
authored a
paper 29 days ago
upvoted 3
papers about 1 month ago
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Paper • 2608.18933 • Published • 13
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
Paper • 2608.13667 • Published • 17
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Paper • 2608.09802 • Published • 83
submitted a
paper to Daily Papers about 1 month ago