Scaling Scientific Discovery Environments for Turn-Level Agentic RLarXiv:2607.28990v1 Announce Type: new Abstract: Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution environment and produces·Research/Agent, LLM, 智能体, +1·arxiv.org ↗arxiv.org ↗
Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental DesignarXiv:2607.28894v1 Announce Type: new Abstract: Computational cognitive modeling seeks to infer latent cognitive mechanisms underlying observed behavior. Bayesian inverse planning provides a principled framework for such·Research/推理优化·arxiv.org ↗arxiv.org ↗
Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent FailuresarXiv:2607.28802v1 Announce Type: new Abstract: Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system. This·Research/Agent, 智能体·arxiv.org ↗arxiv.org ↗
EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter DiagnosesarXiv:2607.28788v1 Announce Type: new Abstract: Clinical diagnosis at hospital admission must be made rapidly from limited, incomplete evidence. Existing diagnosis-prediction benchmarks are poorly suited to this setting:·Research/临床医学·arxiv.org ↗arxiv.org ↗
Safety, or Just Capability? A Validity Audit of Agent-Safety BenchmarksarXiv:2607.28685v1 Announce Type: new Abstract: Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm·Research/Agent, 智能体·arxiv.org ↗arxiv.org ↗
Library Reachability in LSR-Synth: How Anti-Memorization Design Changes the Measurement of Symbolic DiscoveryarXiv:2607.28684v1 Announce Type: new Abstract: Existing benchmarks for scientific equation discovery are largely composed of well-known equations available in the public domain, making it difficult to determine whether·Research/综合科学·arxiv.org ↗arxiv.org ↗
ViSAGE: Constructing Self-Correcting Memories for Long-Form Video UnderstandingarXiv:2607.28678v1 Announce Type: new Abstract: Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning.·Research/多模态, 推理优化, 智能体·arxiv.org ↗arxiv.org ↗
An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous DocumentsarXiv:2607.28662v1 Announce Type: new Abstract: Large language models extract entities and relationships from unstructured documents fluently but inconsistently: type vocabularies fracture across documents, the same pers·Research/LLM·arxiv.org ↗arxiv.org ↗
Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel DecodingarXiv:2607.28659v1 Announce Type: new Abstract: Cross-domain sequential recommendation (CDSR) aims to model users' dynamic interest transitions and sequential patterns across multiple domains. Recently, generative recomm·Research/深度学习, LLM·arxiv.org ↗arxiv.org ↗
ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon ReasoningarXiv:2607.28642v1 Announce Type: new Abstract: Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error anchoring. We argue th·Research/推理优化·arxiv.org ↗arxiv.org ↗
《控制:共振》公布中国独家预告片及专属服装Remedy Entertainment 于日前公布了《控制:共振》中国独家预告片。该预告片为首次发布的中文配音版本。 与此同时,预告片中亦首度展示了为中国玩家专属定制的服装,以此致敬中国玩家社群长久以来的热情与支持。据悉,非物质目标部是首次揭晓、负责处理国内异常的官方机构。该部门负责在国内发现与收容超自然现象,以维系公共秩序。 本作中,玩家将重返屡获殊荣的《控制》世界,在续作中与迪伦并肩探索广阔的腐化都市。混沌希斯四处蔓延,侵入性微生·Research/综合科学·gcores.com ↗gcores.com ↗
Mom or not, caring for babies changes the brainFreeman Hrabowski Scholar Bianca Jones Marlin studies how caregiving takes shape in the brain and how some biological adaptations are passed to the next generation.·Research/综合科学·phys.org ↗phys.org ↗
A cooperative approach to reproductive successFertilization is often imagined as a frantic race, with millions of sperm competing for a single prize. But new research by a team of evolutionary biologists from Syracuse University, the University of Siena in Italy and·Research/综合科学·phys.org ↗phys.org ↗
Newly unearthed mechanism that helps plants 'feel full' could help crops use fertilizer more efficientlyNew York University researchers have pinpointed the molecular players responsible for plants "feeling full" once they've taken up enough nitrogen—a finding that could help scientists develop plants that absorb more·Research/综合科学·phys.org ↗phys.org ↗
Climate change could dramatically reduce water flowing from the West's headwatersThe small mountain streams that feed many of the West's rivers may face a much drier future. A new study led by NAU researchers found that groundwater-fed streamflow, known as base flow, has been steadily declining·Research/环境气候·phys.org ↗phys.org ↗
New microscopy method achieves angstrom-scale localization precision with one laserResearchers in the lab of Sam Peng, the Pfizer Inc.–Gerald Laubach Career Development Assistant Professor of Chemistry at MIT and a core institute member of the Broad Institute of MIT and Harvard, have developed a super-·Research/综合科学·phys.org ↗phys.org ↗
Antibiotic resistance is spreading through South Africa's water systems. This study explains howAntimicrobial resistance (AMR) is defined as the ability of disease-causing microorganisms to withstand treatments like antibiotics.·Research/综合科学·phys.org ↗phys.org ↗
Webb reveals warped structure in nearby TW Hydrae's protoplanetary diskUsing the James Webb Space Telescope (JWST), astronomers obtained high-contrast coronagraphic images of the protoplanetary disk around the young, nearby star TW Hydrae. Results of the observational campaign, published Ju·Research/航天·phys.org ↗phys.org ↗
Supergene solves evolutionary puzzle of mirror-image flowersThe left-right asymmetry of South African butterfly lilies (genus Wachendorfia) has been regarded as a classic evolutionary puzzle for more than a century. Due to the mirror-image arrangement of the floral parts, the pla·Research/生命科学, 综合科学·phys.org ↗phys.org ↗
Re: UK maternity inquiries: 25 years of the same diagnosisAgreement: I Agree Body: Dear Editor A commercial pilot looking out of the cockpit as she lands sees a row of lights beside the runway. The autopilot often flies the plane, but the lights tell the pilot if it is on a saf·Research/综合科学·bmj.com ↗bmj.com ↗