❌

Normal view

Received — 13 April 2026 ⏭

TREM2-mediated microglial phagocytosis of inhibitory synapses contributes to prolonged FS-induced epileptogenesis

✇Cell Death Discovery nature.com science feeds
By: Xiaoqian Wang · Hua Zhou · Yujie Zhai · Yunrong Zhang · Yao Cheng · Yi Yuan · Wenxiao Cao · Anqing Gao · Mengshuang Liu · Qiaoyun Wang · Hongliu Sun
11 April 2026 at 08:00

Cell Death Discovery, Published online: 11 April 2026; doi:10.1038/s41420-026-03118-7

TREM2-mediated microglial phagocytosis of inhibitory synapses contributes to prolonged FS-induced epileptogenesis
Received — 8 April 2026 ⏭

FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zeyu Wang · Xiaogang Li · Peiyao Xiao · Qinhao Kong · Ben Wang · Chengliang Xu · Zichao Chen · Bing Zhao · Hu Wei
7 April 2026 at 12:00
arXiv:2604.03893v1 Announce Type: new Abstract: Breakthroughs in frontier theory often depend on the combination of concrete diagrammatic notations with rigorous logic. While multimodal large language models (MLLMs) show promise in general scientific tasks, current benchmarks often focus on local information extraction rather than the global structural logic inherent in formal scientific notations. In this work, we introduce FeynmanBench, the first benchmark centered on Feynman diagram tasks. It is designed to evaluate AI's capacity for multistep diagrammatic reasoning, which requires satisfying conservation laws and symmetry constraints, identifying graph topology, converting between diagrammatic and algebraic representations, and constructing scattering amplitudes under specific conventions and gauges. To support large-scale and reproducible evaluation, we developed an automated pipeline producing diverse Feynman diagrams along with verifiable topological annotations and amplitude results. Our database spans the electromagnetic, weak, and strong interactions of the Standard Model, encompasses over 100 distinct types and includes more than 2000 tasks. Experiments on state-of-the-art MLLMs reveal systematic failure modes, including unstable enforcement of physical constraints and violations of global topological conditions, highlighting the need for physics-grounded benchmarks for visual reasoning over scientific notation. FeynmanBench provides a logically rigorous test of whether AI can effectively engage in scientific discovery, particularly within theoretical physics.

Determined by User Needs: A Salient Object Detection Rationale Beyond Conventional Visual Stimuli

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chenglizhao Chen · Shujian Zhang · Luming Li · Wenfeng Song · Shuai Li
7 April 2026 at 12:00
arXiv:2604.03526v1 Announce Type: cross Abstract: Existing \textbf{s}alient \textbf{o}bject \textbf{d}etection (SOD) methods adopt a \textbf{passive} visual stimulus-based rationale--objects with the strongest visual stimuli are perceived as the user's primary focus (i.e., salient objects). They ignore the decisive role of users' \textbf{proactive needs} in segmenting salient objects--if a user has a need before seeing an image, the user's salient objects align with their needs, e.g., if a user's need is ``white apple'', when this user sees an image, the user's primary focus is on the ``white apple'' or ``the most white apple-like'' objects in the image. Such an oversight not only \textbf{fails to satisfy users}, but also \textbf{limits the development of downstream tasks}. For instance, in salient object ranking tasks, focusing solely on visual stimuli-based salient objects is insufficient for conducting an analysis of fine-grained relationships between users' viewing order (usually determined by user's needs) and scenes, which may result in wrong ranking results. Clearly, it is essential to detect salient objects based on user needs. Thus, we advocate a \textbf{User} \textbf{S}alient \textbf{O}bject \textbf{D}etection (UserSOD) task, which focuses on \textbf{detecting salient objects align with users' proactive needs when user have needs}. The main challenge for this new task is the lack of datasets for model training and testing.

Agentization of Digital Assets for the Agentic Web: Concepts, Techniques, and Benchmark

✇cs.AI, q-bio.NC updates on arXiv.org
By: Linyao Chen · Bo Huang · Qinlao Zhao · Shuai Shao · Zhi Han · Zicai Cui · Ziheng Zhang · Guangtao Zeng · Wenzheng Tang · Yikun Wang · Yuanjian Zhou · Zimian Peng · Yong Yu · Weiwen Liu · Hiroki Kobayashi · Weinan Zhang
7 April 2026 at 12:00
arXiv:2604.04226v1 Announce Type: cross Abstract: Agentic Web, as a new paradigm that redefines the internet through autonomous, goal-driven interactions, plays an important role in group intelligence. As the foundational semantic primitives of the Agentic Web, digital assets encapsulate interactive web elements into agents, which expand the capacities and coverage of agents in agentic web. The lack of automated methodologies for agent generation limits the wider usage of digital assets and the advancement of the Agentic Web. In this paper, we first formalize these challenges by strictly defining the A2A-Agentization process, decomposing it into critical stages and identifying key technical hurdles on top of the A2A protocol. Based on this framework, we develop an Agentization Agent to agentize digital assets for the Agentic Web. To rigorously evaluate this capability, we propose A2A-Agentization Bench, the first benchmark explicitly designed to evaluate agentization quality in terms of fidelity and interoperability. Our experiments demonstrate that our approach effectively activates the functional capabilities of digital assets and enables interoperable A2A multi-agent collaboration. We believe this work will further facilitate scalable and standardized integration of digital assets into the Agentic Web ecosystem.

Discrete Prototypical Memories for Federated Time Series Foundation Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Liwei Deng · Qingxiang Liu · Xinhe Niu · Shengchao Chen · Sheng Sun · Yuankai Wu · Guodong Long · Yuxuan Liang
7 April 2026 at 12:00
arXiv:2604.04475v1 Announce Type: cross Abstract: Leveraging Large Language Models (LLMs) as federated learning (FL)-based time series foundation models offers a promising way to transfer the generalization capabilities of LLMs to time series data while preserving access to private data. However, the semantic misalignment between time-series data and the text-centric latent space of existing LLMs often leads to degraded performance. Meanwhile, the parameter-sharing mechanism in existing FL methods model heterogeneous cross-domain time-series data into a unified continuous latent space, which contradicts the fact that time-series semantics frequently manifest as discrete and recurring regimes. To address these limitations, we propose \textsc{FeDPM}, a federated framework for time-series foundation models based on discrete prototypical memories. Specifically, we learn local prototypical memory priors for intra-domain time-series data. We then align cross-domain memories to promote a unified discrete latent space and introduce a domain-specific memory update mechanism to balance shared and personalized prototypical knowledge. Extensive experiments demonstrate the efficiency and effectiveness of \textsc{FeDPM}. The code is publicly available at https://anonymous.4open.science/r/FedUnit-64D1.

Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Justin Chih-Yao Chen · Archiki Prasad · Zaid Khan · Joykirat Singh · Runchu Tian · Elias Stengel-Eskin · Mohit Bansal
7 April 2026 at 12:00
arXiv:2604.04767v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of LLMs, yet a fundamental limitation remains: models cannot learn from problems that are too difficult to solve under their current policy, as these yield no meaningful reward signal. We propose a simple yet effective solution based on task reformulation. We transform challenging open-ended problems into cognitively simpler variants -- such as multiple-choice and cloze formats -- that preserve the original answer while reducing the effective search space and providing denser learning signals. These reformulations span a spectrum from discriminative to generative tasks, which we exploit to bootstrap learning: models first learn from structured, easier formats, and this knowledge transfers back to improve performance on the original open-ended problems. Building on this insight, we introduce Cog-DRIFT, a framework that constructs reformulated variants and organizes them into an adaptive curriculum based on difficulty. Training progresses from easier to harder formats, enabling the model to learn from problems that previously yielded zero signal under standard RL post-training. Cog-DRIFT not only improves on the originally unsolvable hard problems (absolute +10.11% for Qwen and +8.64% for Llama) but also generalizes well to other held-out datasets. Across 2 models and 6 reasoning benchmarks, our method consistently outperforms standard GRPO and strong guided-exploration baselines. On average, Cog-DRIFT shows +4.72% (Qwen) and +3.23% (Llama) improvements over the second-best baseline. We further show that Cog-DRIFT improves pass@k at test time, and the curriculum improves sample efficiency. Overall, our results highlight task reformulation and curriculum learning as an effective paradigm for overcoming the exploration barrier in LLM post-training.
Received — 6 April 2026 ⏭

Spliceosomal component SNRPE drives cell proliferation by regulating CTP synthase 1 mRNA splicing in ovarian cancer

✇Oncogene - Issue - nature.com science feeds
By: Yingying Pu · Zhongshao Chen · Qianqian Gao · Yanling Liu · Ning Yang · Yingwei Li · Beihua Kong
4 April 2026 at 08:00

Oncogene, Published online: 04 April 2026; doi:10.1038/s41388-026-03764-2

Spliceosomal component SNRPE drives cell proliferation by regulating CTP synthase 1 mRNA splicing in ovarian cancer

Isobavachalcone exerts anti-gastric cancer effects by targeting dihydroorotate dehydrogenase to induce ROS release and activating the STING pathway

✇Omics in Gastric
By: Yong Kuang · Yu Shao · Jia Chen · Chen Dai · Sachiyo Nomura · Fulin Wang · Jingyao Chen · Yulong He · Xing Xiao · Changhua Zhang · Jiahao Feng
3 April 2026 at 18:00

Phytomedicine. 2026 Mar 27;155:158126. doi: 10.1016/j.phymed.2026.158126. Online ahead of print.

ABSTRACT

BACKGROUND: Mitochondrial damage can induce the release of mitochondrial DNA (mtDNA), leading to oxidative stress and activation of immune responses. Targeting mitochondrial dysfunction may thus represent a therapeutic strategy for gastric cancer. Isobavachalcone (IBC), a prenylated chalcone derived from Psoralea corylifolia L., has demonstrated antitumor activity, but its mechanism of action remains unclear, limiting its clinical application.

PURPOSE: This study aimed to investigate the antitumor effects of IBC in gastric cancer and to elucidate the underlying molecular mechanisms, with a focus on mitochondrial damage and immune activation.

STUDY DESIGN: The study combined in vitro and in vivo assays with multi-omics sequencing and network pharmacology to identify IBC's therapeutic target and downstream signaling pathways.

METHODS: Gastric cancer cells and mouse models were treated with IBC to assess its inhibitory effects. Multi-omics approaches and network pharmacology were used to identify potential targets. ROS production, mitochondrial membrane integrity, and immune pathway activation were evaluated via biochemical and molecular assays.

RESULTS: IBC significantly suppresses gastric cancer growth both in vitro and in vivo. Integrated analysis identifies dihydroorotate dehydrogenase (DHODH) as a direct target of IBC. DHODH deficiency can induce mitochondrial membrane remodeling and STING pathway activation. Inhibition of DHODH by IBC induces ROS accumulation, mitochondrial membrane remodeling, and activation of the STING pathway, promoting antitumor immune responses. This study demonstrates that IBC enhances antitumor immunity in gastric cancer through mitochondrial damage-mediated mechanisms.

CONCLUSION: IBC exerts dual antitumor and immunostimulatory effects in gastric cancer by targeting DHODH, inducing mitochondrial damage, and activating the STING pathway, highlighting its promising therapeutic potential in gastric cancer.

PMID:41931998 | DOI:10.1016/j.phymed.2026.158126

Isobavachalcone exerts anti-gastric cancer effects by targeting dihydroorotate dehydrogenase to induce ROS release and activating the STING pathway

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yong Kuang · Yu Shao · Jia Chen · Chen Dai · Sachiyo Nomura · Fulin Wang · Jingyao Chen · Yulong He · Xing Xiao · Changhua Zhang · Jiahao Feng
3 April 2026 at 18:00

Phytomedicine. 2026 Mar 27;155:158126. doi: 10.1016/j.phymed.2026.158126. Online ahead of print.

ABSTRACT

BACKGROUND: Mitochondrial damage can induce the release of mitochondrial DNA (mtDNA), leading to oxidative stress and activation of immune responses. Targeting mitochondrial dysfunction may thus represent a therapeutic strategy for gastric cancer. Isobavachalcone (IBC), a prenylated chalcone derived from Psoralea corylifolia L., has demonstrated antitumor activity, but its mechanism of action remains unclear, limiting its clinical application.

PURPOSE: This study aimed to investigate the antitumor effects of IBC in gastric cancer and to elucidate the underlying molecular mechanisms, with a focus on mitochondrial damage and immune activation.

STUDY DESIGN: The study combined in vitro and in vivo assays with multi-omics sequencing and network pharmacology to identify IBC's therapeutic target and downstream signaling pathways.

METHODS: Gastric cancer cells and mouse models were treated with IBC to assess its inhibitory effects. Multi-omics approaches and network pharmacology were used to identify potential targets. ROS production, mitochondrial membrane integrity, and immune pathway activation were evaluated via biochemical and molecular assays.

RESULTS: IBC significantly suppresses gastric cancer growth both in vitro and in vivo. Integrated analysis identifies dihydroorotate dehydrogenase (DHODH) as a direct target of IBC. DHODH deficiency can induce mitochondrial membrane remodeling and STING pathway activation. Inhibition of DHODH by IBC induces ROS accumulation, mitochondrial membrane remodeling, and activation of the STING pathway, promoting antitumor immune responses. This study demonstrates that IBC enhances antitumor immunity in gastric cancer through mitochondrial damage-mediated mechanisms.

CONCLUSION: IBC exerts dual antitumor and immunostimulatory effects in gastric cancer by targeting DHODH, inducing mitochondrial damage, and activating the STING pathway, highlighting its promising therapeutic potential in gastric cancer.

PMID:41931998 | DOI:10.1016/j.phymed.2026.158126

Received — 4 April 2026 ⏭

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xinlei Yu · Zhangquan Chen · Yongbo He · Tianyu Fu · Cheng Yang · Chengming Xu · Yue Ma · Xiaobin Hu · Zhe Cao · Jie Xu · Guibin Zhang · Jiale Tao · Jiayi Zhang · Siyuan Ma · Kaituo Feng · Haojie Huang · Youxing Li · Ronghao Chen · Huacan Wang · Chenglin Wu · Zikun Su · Xiaogang Xu · Kelu Yao · Kun Wang · Chen Gao · Yue Liao · Ruqi Huang · Tao Jin · Cheng Tan · Jiangning Zhang · Wenqi Ren · Yanwei Fu · Yong Liu · Yu Wang · Xiangyu Yue · Yu-Gang Jiang · Shuicheng Yan
3 April 2026 at 12:00
arXiv:2604.02029v1 Announce Type: new Abstract: Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an increasing body of work shows that many critical internal processes are more naturally carried out in continuous latent space than in human-readable verbal traces. This shift is driven by the structural limitations of explicit-space computation, including linguistic redundancy, discretization bottlenecks, sequential inefficiency, and semantic loss. This survey aims to provide a unified and up-to-date landscape of latent space in language-based models. We organize the survey into five sequential perspectives: Foundation, Evolution, Mechanism, Ability, and Outlook. We begin by delineating the scope of latent space, distinguishing it from explicit or verbal space and from the latent spaces commonly studied in generative visual models. We then trace the field's evolution from early exploratory efforts to the current large-scale expansion. To organize the technical landscape, we examine existing work through the complementary lenses of mechanism and ability. From the perspective of Mechanism, we identify four major lines of development: Architecture, Representation, Computation, and Optimization. From the perspective of Ability, we show how latent space supports a broad capability spectrum spanning Reasoning, Planning, Modeling, Perception, Memory, Collaboration, and Embodiment. Beyond consolidation, we discuss the key open challenges, and outline promising directions for future research. We hope this survey serves not only as a reference for existing work, but also as a foundation for understanding latent space as a general computational and systems paradigm for next-generation intelligence.

DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guanzhi Deng · Bo Li · Ronghao Chen · Xiujin Liu · Zhuo Han · Huacan Wang · Lijie Wen · Linqi Song
3 April 2026 at 12:00
arXiv:2601.04823v5 Announce Type: replace Abstract: Mixture-of-Experts (MoE) has become a prominent paradigm for scaling Large Language Models (LLMs). Parameter-efficient fine-tuning methods, such as LoRA, are widely adopted to adapt pretrained MoE LLMs to downstream tasks. However, existing approaches typically assign identical LoRA ranks to all expert modules, ignoring the heterogeneous specialization of pretrained experts. This uniform allocation leads to a resource mismatch: task-relevant experts are under-provisioned, while less relevant ones receive redundant parameters. To address this, we propose DR-LoRA, a Dynamic Rank LoRA framework for fine-tuning pretrained MoE models. Specifically, DR-LoRA initializes all expert LoRA modules with a small active rank and uses an expert saliency score, which combines routing frequency and gradient-based rank importance, to identify which experts would benefit most from additional capacity. It then periodically expands the active ranks of the task-critical expert LoRA, progressively constructing a heterogeneous rank distribution tailored to the target task. Experiments on three MoE models across six tasks show that DR-LoRA consistently outperforms LoRA and other strong baselines, demonstrating that task-adaptive heterogeneous rank allocation is an effective strategy to improve active capacity utilization in MoE fine-tuning.

Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dachuan Zhao · Weiyue Li · Zhenda Shen · Yushu Qiu · Bowen Xu · Haoyu Chen · Yongchao Chen
3 April 2026 at 12:00
arXiv:2511.18123v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have become indispensable for multimodal reasoning, yet their representations often encode and amplify demographic biases, resulting in biased associations and misaligned predictions in downstream tasks. Such behavior undermines fairness and distorts the intended alignment between vision and language. Recent post-hoc approaches attempt to mitigate bias by replacing the most attribute-correlated embedding coordinates with neutral values. However, our systematic analysis reveals three critical limitations of this coordinate-wise approach: feature entanglement, poor cross-dataset generalization, and incomplete bias removal. We find that bias is not localized to a few coordinates but is instead distributed across a few linear subspaces. To address these limitations, we propose $\textbf{S}$ubspace $\textbf{P}$rojection $\textbf{D}$ebiasing ($\textbf{SPD}$), a geometrically principled framework that identifies and removes the entire subspace of linearly decodable bias while reinserting a neutral mean component to preserve semantic fidelity. Extensive experiments across zero-shot classification, text-to-image retrieval, and image generation validate the effectiveness of SPD: our method achieves more robust debiasing with an average improvement of $18.5\%$ across four fairness metrics, while maintaining minimal loss in task performance compared to the best debiasing baseline.
Received — 2 April 2026 ⏭

Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tao Chen · Kun Zhang · Qiong Wu · Xiao Chen · Chao Chang · Xiaoshuai Sun · Yiyi Zhou · Rongrong Ji
1 April 2026 at 12:00
arXiv:2603.29252v1 Announce Type: cross Abstract: Long video understanding is a key challenge that plagues the advancement of \emph{Multimodal Large language Models} (MLLMs). In this paper, we study this problem from the perspective of visual memory mechanism, and proposed a novel and training-free approach, termed \emph{Flexible Memory} (\textbf{FlexMem}). In principle, FlexMem aims to mimic human behavior of video watching, \emph{i.e.}, continually watching video content and recalling the most relevant memory fragments to answer the question. In this way, FlexMem can help MLLMs achieve video understanding of infinite lengths, unlike previous methods that process all video information at once and have input upper-limit. Concretely, FlexMem first consider the visual KV caches as the memory sources, and realize the effective memory transfer and writing via a dual-pathway compression design. Afterwards, FlexMem also explores different memory reading strategies for the diverse video understanding tasks, including the popular streaming one. To validate FlexMem, we apply it to two popular video-MLLMs, and conduct extensive experiments on five long video and one streaming video task. The experimental results show that on \textbf{a single 3090 GPU}, our FlexMem can achieve obvious improvements than existing efficient video understanding methods and process more than \textbf{1k frames}, which also helps the base MLLMs achieve comparable or even better performance than SOTA MLLMs on some benchmarks, \emph{e.g.} , GPT-4o and Gemini-1.5 Pro.

6GAgentGym: Tool Use, Data Synthesis, and Agentic Learning for Network Management

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiao Chen · Jianhua Tang · Xiaotong Yang · Zuohong Lv
1 April 2026 at 12:00
arXiv:2603.29656v1 Announce Type: cross Abstract: Autonomous 6G network management requires agents that can execute tools, observe the resulting state changes, and adapt their decisions accordingly. Existing benchmarks based on static questions or scripted episode replay, however, do not support such closed-loop interaction, limiting agents to passive evaluation without the ability to learn from environmental feedback. This paper presents 6GAgentGym to provide closed-loop capability. The framework provides an interactive environment with 42 typed tools whose effect classification distinguishes read-only observation from state-mutating configuration, backed by a learned Experiment Model calibrated on NS-3 simulation data. 6G-Forge bootstraps closed-loop training trajectories from NS-3 seeds via iterative Self-Instruct generation with execution verification against the Experiment Model. Supervised fine-tuning on the resulting corpus followed by reinforcement learning with online closed-loop interaction enables an 8B open-source model to achieve comparable overall success rate to GPT-5 on the accompanying 6GAgentBench, with stronger performance on long-horizon tasks. Together, these components provide a viable path toward autonomous, closed-loop network management.

The 1000 Chinese Pangenome empowers medical and population genetics

✇Nature - Issue - nature.com science feeds
By: Yifei Wang · Zhongqu Duan · Dan Chen · Dandan Shi · Yi Ding · Zhibin Wang · Baoqing Li · Zhiyi Wang · Minmin Guo · Wen Yang · Junren Hou · Wenhao Chen · Yazhou Guo · Wenjie Wei · Yujie Cao · Xiwei Sun · Weiyang Bai · Mingdong Lu · Ting Qi · Xian Shen · Jian Yang
1 April 2026 at 08:00

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10315-y

Development of the pangenome-informed genome assembly (PIGA) workflow enabled the generation of 1,116 diploid genome assemblies (55 de novo and 1,061 pangenome-informed), representing an extensive resource of medically relevant genic variations.
Received — 26 March 2026 ⏭

PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shuochen Liu · Junyi Zhu · Long Shu · Junda Lin · Yuhao Chen · Haotian Zhang · Chao Zhang · Derong Xu · Jia Li · Bo Tang · Zhiyu Li · Feiyu Xiong · Enhong Chen · Tong Xu
25 March 2026 at 12:00
arXiv:2603.23231v1 Announce Type: new Abstract: Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. However, prior evaluations typically interleave preference-related dialogues with irrelevant conversations, reducing the task to needle-in-a-haystack retrieval while ignoring relationships between events that drive the evolution of user preferences. Such settings overlook a fundamental characteristic of real-world personalization: preferences emerge gradually and accumulate across interactions within noisy contexts. To bridge this gap, we introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall. Additionally, we incorporate (1) text variability and (2) linguistic alignment to simulate erratic user inputs and individual idiolects in real-world data. PERMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time. We design both multiple-choice and interactive tasks to probe the model's understanding of persona along the interaction timeline. Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption, outperforming traditional semantic retrieval of raw dialogues. Nevertheless, they still struggle to maintain a coherent persona across temporal depth and cross-domain interference, highlighting the need for more robust personalized memory management in agents. Our code and data are open-sourced at https://github.com/PolarisLiu1/PERMA.

ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shaobo Ju · Baiyang Song · Tao Chen · Jiapeng Zhang · Qiong Wu · Chao Chang · HuaiXi Wang · Yiyi Zhou · Rongrong Ji
25 March 2026 at 12:00
arXiv:2603.22911v1 Announce Type: cross Abstract: Due to the great saving of computation and memory overhead, token compression has become a research hot-spot for MLLMs and achieved remarkable progress in image-language tasks. However, for the video, existing methods still fall short of high-ratio token compression. We attribute this shortcoming to the insufficient modeling of temporal and continual video content, and propose a novel and training-free token pruning method for video MLLMs, termed ForestPrune, which achieves effective and high-ratio pruning via Spatial-temporal Forest Modeling. In practice, ForestPrune construct token forests across video frames based on the semantic, spatial and temporal constraints, making an overall comprehension of videos. Afterwards, ForestPrune evaluates the importance of token trees and nodes based on tree depth and node roles, thereby obtaining a globally optimal pruning decision. To validate ForestPrune, we apply it to two representative video MLLMs, namely LLaVA-Video and LLaVA-OneVision, and conduct extensive experiments on a bunch of video benchmarks. The experimental results not only show the great effectiveness for video MLLMs, e.g., retaining 95.8% average accuracy while reducing 90% tokens for LLaVA-OneVision, but also show its superior performance and efficiency than the compared token compression methods, e.g., +10.1% accuracy on MLVU and -81.4% pruning time than FrameFusion on LLaVA-Video.

ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hao Wang · Haocheng Yang · Licheng Pan · Lei Shen · Xiaoxi Li · Yinuo Wang · Zhichao Chen · Yuan Lu · Haoxuan Li · Zhouchen Lin
25 March 2026 at 12:00
arXiv:2603.23184v1 Announce Type: cross Abstract: Reward modeling represents a long-standing challenge in reinforcement learning from human feedback (RLHF) for aligning language models. Current reward modeling is heavily contingent upon experimental feedback data with high collection costs. In this work, we study \textit{implicit reward modeling} -- learning reward models from implicit human feedback (e.g., clicks and copies) -- as a cost-effective alternative. We identify two fundamental challenges in implicit reward modeling: (1) Implicit preference data lacks definitive negative samples, which makes standard positive-negative classification methods inapplicable; (2) Implicit preference data suffers from user preference bias, where different responses have different propensities to elicit user feedback actions, which exacerbates the difficulty of distinguishing definitive negative samples. To address these challenges, we propose ImplicitRM, which aims to learn unbiased reward models from implicit preference data. ImplicitRM stratifies training samples into four latent groups via a stratification model. Building on this, it derives a learning objective through likelihood maximization, which we prove is theoretically unbiased, effectively resolving both challenges. Experiments demonstrate that ImplicitRM learns accurate reward models across implicit preference datasets. Code is available on our project website.

TRACE: A Multi-Agent System for Autonomous Physical Reasoning in Seismological

✇cs.AI, q-bio.NC updates on arXiv.org
By: Feng Liu · Jian Xu · Xin Cui · Xinghao Wang · Zijie Guo · Jiong Wang · S. Mostafa Mousavi · Xinyu Gu · Hao Chen · Ben Fei · Lihua Fang · Fenghua Ling · Zefeng Li · Lei Bai
25 March 2026 at 12:00
arXiv:2603.21152v2 Announce Type: replace-cross Abstract: Inferring the physical mechanisms that govern earthquake sequences from indirect geophysical observations remains difficult, particularly across tectonically distinct environments where similar seismic patterns can reflect different underlying processes. Current interpretations rely heavily on the expert synthesis of catalogs, spatiotemporal statistics, and candidate physical models, limiting reproducibility and the systematic transfer of insight across settings. Here we present TRACE (Trans-perspective Reasoning and Automated Comprehensive Evaluator), a multi-agent system that combines large language model planning with formal seismological constraints to derive auditable, physically grounded mechanistic inference from raw observations. Applied to the 2019 Ridgecrest sequence, TRACE autonomously identifies stress-perturbation-induced delayed triggering, resolving the cascading interaction between the Mw 6.4 and Mw 7.1 mainshocks; in the Santorini-Kolumbo case, the system identifies a structurally guided intrusion model, distinguishing fault-channeled episodic migration from the continuous propagation expected in homogeneous crustal failure. By providing a generalizable logical infrastructure for interpreting heterogeneous seismic phenomena, TRACE advances the field from expert-dependent analysis toward knowledge-guided autonomous discovery in Earth sciences.
❌