6 papers
QAM: Quadratic-Accurate Checkpoint Merging via Sequential Consistency
Shihao Wang, Rui Kong, Xinran Chen +7
Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a different schedule. We study how acc…
SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches
Tores Julie, Sun Rémy, Sassatelli Lucile +3
Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task performance but little transparen…
From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents
Shuoling Liu, Zhiquan Tan, Kun Yi +6
Deep Research Agents (DRAs) aim to answer complex questions by searching the web, checking evidence, and synthesizing conclusions across heterogeneous sources. We introduce a categ…
MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
Hui Wu, Haoquan Zhai, Yuchen Li +8
Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmente…
Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment
Hui Wu, Hengyi Cai, Jinman Zhao +6
Offline preference optimization aligns reasoning models from fixed chosen--rejected pairs, yet standard methods apply gradient updates from every pair regardless of its training va…
Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
Ziheng Li, Zexu Sun, Jinman Zhao +8
Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, existing RLV…