R1-Searcher uses two-stage outcome-based RL to train LLMs to invoke external search systems for better reasoning without process rewards or distillation.
Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
Ada-KV is the first head-wise adaptive KV cache budget allocator for LLMs, using a theoretical loss upper bound to allocate eviction differently per attention head and yielding higher quality than uniform methods on long-context benchmarks.
citing papers explorer
-
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
R1-Searcher uses two-stage outcome-based RL to train LLMs to invoke external search systems for better reasoning without process rewards or distillation.
-
Supervising the search process produces reliable and generalizable information-seeking agents
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
-
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
Ada-KV is the first head-wise adaptive KV cache budget allocator for LLMs, using a theoretical loss upper bound to allocate eviction differently per attention head and yielding higher quality than uniform methods on long-context benchmarks.