#Recursive self-improvement (3)

Waterfall Pagination

0:27

AREX: A Recursively Self-Improving Deep Research Agent from BAAI

@BAAIBeijing · 46 views · 2026-09-11

Deep Research AgentRecursive self-improvementAgentic Search

1:00

SoL-Pi: A Token-Efficient Agent Harness Built by Auto-Research Loops

@QihangCao11 · 33 views · 2026-09-11

Agent HarnessRecursive self-improvementToken Efficiency

ModularRSI: Toward Generalizable Harness RSI

ModularRSI decomposes an agent harness into five functional modules, evolves them independently with 2,000 evolution instances disjoint from downstream benchmarks, contrastive trajectory diagnosis, scoped code modification, and validation gates. The TB-evolved harness raises Terminal-Bench 2.0 Acc from 47.57 to 52.43 and transfers across domains and foundation models including GLM-5.2, MiniMax-2.5, and DeepSeek variants.

BLOG

Harness RSIModularRSIAgent HarnessTerminal-Bench 2.0SWE-Bench Verified