VC-Soup uses a cosine-similarity consistency metric to filter data, trains value-consistent policies, and applies linear merging with Pareto filtering to improve multi-value LLM alignment trade-offs.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
baseline 1polarities
baseline 1representative citing papers
MoRE enables MLLMs to dynamically coordinate heterogeneous retrieval experts via Step-GRPO training, yielding over 7% average gains on open-domain QA benchmarks.
Pen-Strategist fine-tunes Qwen-3-14B with RL on a pentesting reasoning dataset and pairs it with a CNN step classifier, reporting 87% better strategy derivation, 47.5% more subtask completions than baselines, and gains on CTFKnow and user studies.
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
citing papers explorer
-
VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
VC-Soup uses a cosine-similarity consistency metric to filter data, trains value-consistent policies, and applies linear merging with Pareto filtering to improve multi-value LLM alignment trade-offs.
-
Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
MoRE enables MLLMs to dynamically coordinate heterogeneous retrieval experts via Step-GRPO training, yielding over 7% average gains on open-domain QA benchmarks.
-
Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis
Pen-Strategist fine-tunes Qwen-3-14B with RL on a pentesting reasoning dataset and pairs it with a CNN step classifier, reporting 87% better strategy derivation, 47.5% more subtask completions than baselines, and gains on CTFKnow and user studies.
-
Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.