INO is an index-time method that uses the production RAG agent to iteratively create, test with queries and paraphrases, reflect on failures, and revise factual nuggets until they are discoverable and used correctly.
Karl: Knowledge agentsvial reinforcement learning.arXiv preprint
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
AgentFugue introduces a plug-in shared reasoning hub trained with SFT and RL that enables peer agents to share intermediate reasoning, yielding gains on long-horizon tasks over strong baselines.
POP bootstraps post-training signals for open-ended LLM tasks by synthesizing rubrics during self-play on pretraining corpus, yielding performance gains on Qwen-2.5-7B across healthcare QA, creative writing, and instruction following.
citing papers explorer
-
Iterate Until Retrieved: Factual Nugget Optimization for Discoverable Continual Corrections in Agentic RAG
INO is an index-time method that uses the production RAG agent to iteratively create, test with queries and paraphrases, reflect on failures, and revise factual nuggets until they are discoverable and used correctly.
-
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
POP bootstraps post-training signals for open-ended LLM tasks by synthesizing rubrics during self-play on pretraining corpus, yielding performance gains on Qwen-2.5-7B across healthcare QA, creative writing, and instruction following.