Papers/2609.04304
🧪 Test?View on arXiv

Iris: Climbing to the Search Frontier

Not specified in the abstract

search agentsreinforcement learningcontext managementdata pipeline
2609.04304
Builder Relevance
80%
7h ago

Abstract

Iris-mini and Iris-pro are advanced search agents that utilize a novel training approach to achieve superior performance on various search benchmarks.

Reality Card

Core Claim

The models achieve the strongest overall results among open-source search agents in their respective parameter ranges, with significant improvements in inference-time context management.

Method / Result

Models reached scores of 88.6/85.1/92.9/56.4 on key benchmarks.

Limitations

The paper does not specify the authors, which may hinder reproducibility and transparency.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers