❌

Normal view

Received — 27 May 2026 ⏭

Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL

✇cs.AI, q-bio.NC updates on arXiv.org
By: Junyi Wu · Weijian Luo · Haoyang Zheng · Ruizhe Zhang · Guang Lin
26 May 2026 at 12:00
arXiv:2605.24001v2 Announce Type: cross Abstract: Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffused Reward Score (DRS), which acts as a reward-driven correction to the reference score function. To make this practical, we further introduce the Diffused Reward Proxy (DRP), an efficient estimator of DRS based on differentiable short-step denoising. Extensive experiments demonstrate that DIDR consistently Pareto-dominates existing one-step SDXL baselines. Moreover, when transferred to a 6B DiT backbone (Z-Image), DIDR surpasses its 50-step teacher in preference alignment while requiring only a single generation step.

OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search

✇cs.AI, q-bio.NC updates on arXiv.org
By: Erhan Zhang · Yiqun Chen · Zechun Niu · Wei Yang · Xiaochi Wei · Yan Gao · Yi Wu · Yao Hu · Jiaxin Mao
26 May 2026 at 12:00
arXiv:2604.03675v3 Announce Type: replace Abstract: Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm for search agents, yet outcome-only rewards are sparse and provide limited credit assignment for intermediate search actions. Existing process-reward methods therefore seek to densify supervision through proxy signals, external evaluators, or likelihood-based information gain. However, proxy rewards can deviate from the final outcome objective, while fixed evaluators can become stale as the search policy evolves, leading to unreliable process supervision. To address these challenges, we propose OASES, an Outcome-Aligned Search-Evaluation Supervision framework for agentic search. OASES derives outcome-aligned process rewards by evaluating how well each intermediate search state supports answering the original question. It further co-trains the search policy and the state evaluator on policy, allowing the evaluator to adapt to evolving search behavior and provide more reliable process rewards. Experiments on five multi-hop QA benchmarks show that OASES consistently outperforms strong RL baselines, with further analyses confirming the benefits of outcome-aligned process rewards and search-evaluation co-training.

UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yijuan Liang · Xinghao Chen · Yifan Ge · Ziyi Wu · Hao Wu · Changyu Zeng · Wei Xing · Xiaoyu Shen
26 May 2026 at 12:00
arXiv:2604.11557v2 Announce Type: replace Abstract: Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However, existing research exhibits inconsistent interaction representations, largely overlooks the structural distribution of tool-use trajectories, and relies on incompatible evaluation benchmarks. We present UniToolCall, a unified framework for tool learning that standardizes the entire pipeline from toolset construction and dataset generation to evaluation. The framework curates a large tool pool of 22k+ tools and constructs a hybrid training corpus of 390k+ instances by combining 10 standardized public datasets with structurally controlled synthetic trajectories. It explicitly models diverse interaction patterns, including single-hop vs. multi-hop and single-turn vs. multi-turn, while capturing both serial and parallel execution structures. To support coherent multi-turn reasoning, we further introduce an Anchor Linkage mechanism that enforces cross-turn dependencies. Furthermore, we convert 7 public benchmarks into a unified Query--Action--Observation--Answer (QAOA) representation with fine-grained evaluation at the function-call, turn, and conversation levels. Experiments show that fine-tuning Qwen3-8B on our dataset substantially improves tool-use performance. Under the distractor-heavy Hybrid-20 setting, achieves 93.0% single-turn Strict Precision, outperforming commercial models including GPT, Gemini, and Claude.

Dynamic microbiome-host interactions and their associations with systemic metabolism and radiological characteristics during early lung adenocarcinoma

✇Pulmonary nodule
By: Qijia Han · Yunfeng Shi · Xinzhu Yi · Zhu Ai · Minyi Wu · Tianshuai He · Xinru Jing · Zhang Wang · Zhiming Xiang
12 May 2026 at 18:00

NPJ Precis Oncol. 2026 May 12;10(1):284. doi: 10.1038/s41698-026-01471-5.

ABSTRACT

Lung adenocarcinoma (LUAD) accounts for approximately 40% of non-small cell lung cancer. Although the microbiome may play a role in LUAD, a comprehensive understanding of its ecological landscape and interactions with the tumor host, particularly during early development of LUAD, remains lacking. Here we employed a multi-omic approach to assess the dynamics of the tumor microbiota-host interaction across stages of early LUAD, including benign nodules, adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC). We found a strong and intricate interaction between the microbiome and host immune and metabolic pathways in AIS, while microbiome-host interactions substantially diminish in MIA and IAC. Serum metabolites and CT-based radiological features, such as atropaldehyde, sterculic acid, nodule morphology and maximum nodule diameter, were closely associated with the microbiome-host interaction network, suggesting they could be non-invasive markers indicating tumor ecological and pathological changes. Multi-omic integration revealed an optimal performance in classifying individual LUAD stages, particularly between AIS and MIA that was otherwise challenging to differentiate using a single data type. Our results highlight the dynamic interaction between microbiome and host during early LUAD, which can be partially reflected in systemic metabolic and radiological manifestations, providing a novel framework for understanding early-stage LUAD.

PMID:42120518 | PMC:PMC13388699 | DOI:10.1038/s41698-026-01471-5

Transplantation of encapsulated mitochondria alleviates dysfunction in mitochondrial and Parkinson’s disease models

✇Cell
By: Shiwei Du · Qi Long · Yanshuang Zhou · Jiangqin Fu · Hao Wu · Liang Yang · Yaohang Xie · Yingzhe Ding · Maolei Zhang · Jingyi Guo · Mengfei Wang · Jiajun Lin · Mingli Hu · Jian Zhang · Deyang Yao · Wei Li · Feixiang Bao · Ge Xiang · Yi Wu · Yile Huang · Haozhao Liang · Rui Wang · Heying Li · Baodan Chen · Chong Li · Junwei Wang · Jiwei Zhang · Dajiang Qin · Jianwei Sun · Yun Zhu · Fei Sun · Wuming Wang · Gang Lu · Wai-Yee Chan · Hui Zhao · Chenli Liu · Xingguo Liu
18 March 2026 at 08:00
A mitochondrial transplantation approach rescues mitochondrial deficiency and prevents mitochondrial DNA depletion syndrome, Leigh syndrome, and Parkinson’s disease in cellular and mouse models.
There are no more articles
❌