Topic
long-horizon
Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents
A new research paper formulates memory retention in long-horizon language agents as a constrained stochastic optimization problem, proposing OSL-MR (Observability-Safe Learning for Memory Retention). The method combines an evidence learner with a Mixed-Score heuristic, achieving superior performance under tight budgets on benchmarks LoCoMo and LongMemEval. The work establishes a principled foundation for memory management in AI agents.
EV-WM: Event-Verified World Models Boost Long-Horizon Robotic Manipulation for Industrial Automation
A research paper introduces EV-WM, a predicate-grounded verification framework for world-model planning in robotic manipulation. By decoding candidate futures into structured event states and scoring them on task-progress, semantic-consistency, physical-feasibility, and uncertainty, EV-WM makes long-horizon planning more interpretable and aligned with task goals. The approach shows promising results in navigation, deformable-object handling, and contact-sensitive tasks, suggesting potential for supply chain and logistics automation.
Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development
A recent arXiv paper by Almalki and Masud provides a structured analysis of security challenges in long-horizon agentic AI systems. It reviews existing threats, evaluation approaches, attack propagation mechanisms, and security frameworks, and proposes a taxonomy of threats and a framework for analyzing attack propagation to support future research.
S1-DeepResearch: New AI Agent Combines Search and Synthesis for Long-Horizon Research Tasks
Researchers introduce S1-DeepResearch, a unified framework for training deep research agents that combine closed-ended QA with open-ended exploration. The 32B-parameter model achieves state-of-the-art among open-source models across 20 benchmarks spanning reasoning, instruction following, report generation, file understanding, and skills usage.
Steady-Forcing: New AI Framework Balances Spatial Persistence and Motion in Long-Horizon Nature Video Generation
A team of researchers has introduced Steady-Forcing, a framework designed to address the stability-motion trade-off in long-horizon nature video generation. The method combines a persistent visual anchor, motion memory, and distillation from a large teacher model to maintain background identity while sustaining fluid dynamics over multi-minute rollouts.