The paper explores proactive agents' ability to seek unstated information, distinguishing between horizontal proactivity (pursuing information within the current context) and vertical proactivity (identifying needs revealed by earlier evidence). It introduces Q&D, a method that trains a questioner to prioritize questions that retrieve more required evidence without a reward model. On multi-hop QA benchmarks, the trained questioner outperforms larger models in proactivity and task completion while asking fewer questions.
The chart will appear after repeat observations. The current metric comes from the source.
4 source votesReal observations only. History before source connection is not reconstructed.
This research advances proactive agents by focusing on the content of their actions rather than just whether they act independently, showing improved task completion with fewer questions.
The paper introduces VisionHOPE, a novel visual backbone that functions as a self-modifying learning system, allowing the model to co-evolve what it remembers and how it learns within an image. It uses five coupled memories and a stability-matched step-size control scheme to ensure stable learning dynamics, achieving competitive results on benchmark datasets like ImageNet-1K, COCO, and ADE20K.
3 days agoDaily PapersThe paper explores the linearity in Large Language Models (LLMs) by showing that combining inputs from different text streams leads to a superposition of next-token distributions. It suggests that this linearity is an inherent property of the Transformer architecture and can be restored through fine-tuning, allowing for generating two coherent continuations from one forward pass.
6 days agoDaily PapersThis paper introduces FuseReg, a method that replaces heuristic layer fusion in representation autoencoders (RAEs) with training over random subsets of encoder layers. The approach reduces the reconstruction-generation gap by improving robustness to layer fusion choices, achieving higher PSNR and lower generation FID scores without modifying the pretrained encoder.
5 days agoDaily PapersThe paper introduces Omni-IO Skills, a plug-and-play agent harness that enables existing agents to handle multiple modalities through hierarchical skills, standardized execution interfaces, and dependency-aware orchestration. It demonstrates significant improvements in input support and semantic quality scores when applied to GPT-5.6 Sol and Claude Sonnet 5 on the UniM-90 dataset.
5 days agoDaily PapersThe paper introduces GAGAR, a framework for quality-aware credit redistribution in code agent reinforcement learning (RL). It uses dynamic sampling and an SFT-trained agentic grader to rank test-passing trajectories, adjusting advantages to prioritize higher-quality implementations. The method was evaluated on large-scale industrial code agents with significant parameter counts.
4 days agoDaily PapersThis paper introduces SentZero, a sentence-centric vision-language pretraining framework designed for zero-shot multi-task analysis of chest X-rays. It enhances positive-pair diversity and mitigates false negatives through LLM-based sentence structuring and visual embedding modulation.
2 days ago