arXiv AI
AgentOCR: Reimagining Agent History via Optical Self-Compression
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 1
When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents
arXiv:2608.29897v1 Announce Type: new Abstract: Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active s...
arXiv AI
Aug 11
Reading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text Compression
arXiv:2608. 08960v1 Announce Type: new Abstract: Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs.
arXiv Computer Vision
2d ago
Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding
arXiv:2609.11899v1 Announce Type: new Abstract: Long-video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual tokens loses t...
arXiv AI
Jun 30
ManimAgent: Self-Evolving Multimodal Agents for Visual Education
arXiv:2606. 30296v1 Announce Type: new Abstract: Multi-round reflection lets agents built on large language models recover from failures within a single task, but each task remains an isolated episode: lessons learned across many reflection rounds on one task are discarded before the next begins.
arXiv AI
Jun 9
ASH: Agents that Self-Hone via Embodied Learning
arXiv:2605. 14211v3 Announce Type: replace Abstract: Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales.
arXiv Machine Learning
Sep 3
DynaTokens: Controlling Token Dynamics for Continual Video-Language Understanding
The paper introduces DynaTokens, a transformer-based token generator that produces fine‑tuning tokens on demand for continual VideoQA with multimodal large language models. It uses shared generation weights and meta‑learning‑inspired regularisers to reduce task interference and forgetting, connecting the objective to sharpness‑aware optimisation for flatter cross‑task minima. Experiments on standard continual VideoQA benchmarks show that DynaTokens achieves higher average accuracy, lower forgetting, better zero‑shot generalisation, and robust cross‑modal transfer in a new ImageQA→VideoQA protocol.