Tags

122 个页面

Reading

Group Sequence Policy Optimization

Towards Effective Code-Integrated Reasoning

Routine：A Structural Planning Framework for LLM Agent System in Enterprise

Search and Refine During Think：Autonomous Retrieval - Augmented Reasoning of LLMs

Peri-LN：Revisiting Normalization Layer in the Transformer Architecture

ZEROSEARCH：Incentivize the Search Capability of LLMs without Searching

First Return, Entropy-Eliciting Explore

Reinforcing General Reasoning without Verifiers

GENERALIST REWARD MODELS：FOUND INSIDE LARGE LANGUAGE MODELS

RLPR：EXTRAPOLATING RLVR TO GENERAL DOMAINS WITHOUT VERIFIERS