SearchEyes unifies multimodal search-agent training via Perception-Knowledge Chains on Wikidata5M and Hop-Anchored Policy Optimization, claiming a 6.2-point average gain over the strongest open-source baseline on six benchmarks.
arXiv preprint arXiv:2509.24726 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
D²Evo mines medium-difficulty anchors from the current model, trains a Questioner to generate matching questions, and jointly optimizes Solver and Questioner for progressive gains, outperforming baselines on math reasoning with under 2K real samples.
Randomly masking a proposer's output vocabulary during training and generation sustains curriculum diversity and improves solver accuracy by +4.4 points at 8B in LLM co-evolution.
A reasoning-driven problem generator plans synthesis directions with CoT and uses solver performance feedback to adapt difficulty, producing complementary problems that yield a 3.4% average improvement across 10 reasoning benchmarks.
citing papers explorer
-
SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation
SearchEyes unifies multimodal search-agent training via Perception-Knowledge Chains on Wikidata5M and Hop-Anchored Policy Optimization, claiming a 6.2-point average gain over the strongest open-source baseline on six benchmarks.
-
D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
D²Evo mines medium-difficulty anchors from the current model, trains a Questioner to generate matching questions, and jointly optimizes Solver and Questioner for progressive gains, outperforming baselines on math reasoning with under 2K real samples.
-
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Randomly masking a proposer's output vocabulary during training and generation sustains curriculum diversity and improves solver accuracy by +4.4 points at 8B in LLM co-evolution.
-
Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis
A reasoning-driven problem generator plans synthesis directions with CoT and uses solver performance feedback to adapt difficulty, producing complementary problems that yield a 3.4% average improvement across 10 reasoning benchmarks.