·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Right Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT58m◆SAGE: A Statistical Acceptance Gate for Self-Evolving Agents58m◆PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning58m◆GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning58m◆Mirror-Score: Calibrated, Inference-only Scoring Exposes the Limits of Sequence-compatibility Ranking in D-peptide Design58m◆SMat-Attention: Structured Long-Context Sequence Modeling58m◆LongCat-DeepResearch Technical Report58m◆A Polyphonic Conception of AI Understanding58m◆GeoOutageBench: Benchmarking Ambiguity-aware, Ontology-grounded Geospatiotemporal KGQA for Multimodal Power Outage and Resilience Analysis58m◆An Exact Generate - Transform Decomposition of Small-LLM Team Scaling Across Orchestration Architectures58m◆The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interface58m◆AdaST: Adaptive Coupling for Spatial-Temporal Forecasting58m◆Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents58m◆More Features Are Not More Evidence: Limits of Training-Free Human Activity Recognition with Jev58m◆Principled Thoughts for Latent Recursive LLM Systems58m◆FigAct: Turning Scientific Figures into Active Canvases for Explanation58m◆An Empirical Study and Assessment of EU AI Act Compliance Checkers58m◆MERID: Multimodal Exploration via Recursive Self-Improvement Agents for Major Depression Analysis58m◆ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning58m◆CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models58m◆Right Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT58m◆SAGE: A Statistical Acceptance Gate for Self-Evolving Agents58m◆PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning58m◆GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning58m◆Mirror-Score: Calibrated, Inference-only Scoring Exposes the Limits of Sequence-compatibility Ranking in D-peptide Design58m◆SMat-Attention: Structured Long-Context Sequence Modeling58m◆LongCat-DeepResearch Technical Report58m◆A Polyphonic Conception of AI Understanding58m◆GeoOutageBench: Benchmarking Ambiguity-aware, Ontology-grounded Geospatiotemporal KGQA for Multimodal Power Outage and Resilience Analysis58m◆An Exact Generate - Transform Decomposition of Small-LLM Team Scaling Across Orchestration Architectures58m◆The Layer Mystery of VLA: An Information-Theoretical Analysis of VLA Latent Interface58m◆AdaST: Adaptive Coupling for Spatial-Temporal Forecasting58m◆Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents58m◆More Features Are Not More Evidence: Limits of Training-Free Human Activity Recognition with Jev58m◆Principled Thoughts for Latent Recursive LLM Systems58m◆FigAct: Turning Scientific Figures into Active Canvases for Explanation58m◆An Empirical Study and Assessment of EU AI Act Compliance Checkers58m◆MERID: Multimodal Exploration via Recursive Self-Improvement Agents for Major Depression Analysis58m◆ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning58m◆CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models58m◆
News/Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents
arxiv
PublishedSeptember 30, 2026 at 4:00 AM

Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2609.36130v1 Announce Type: new Abstract: Long-running LLM agents compress past interactions into persistent memories that may be reused as premises for later tasks. This creates a distinct derivation problem: whether the memory actually follows from what the interaction history supports. Rele

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivRight Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT58marxivSAGE: A Statistical Acceptance Gate for Self-Evolving Agents58marxivPowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning58marxivGeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning58m
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
Built by Marouane Gazouzi
HomeModelsNews