AINeutralarXiv – CS AI · Jun 86/10
🧠ChronoForest introduces a closed-loop planning system that enables efficient long-horizon route planning by composing short offline trajectories, achieving 99.8% success on complex navigation benchmarks. The system addresses a critical challenge in offline navigation where collecting extensive long-range training data is impractical but agents must still solve extended tasks optimally.
AIBullisharXiv – CS AI · Jun 56/10
🧠TokenMizer is an open-source proxy system that addresses a critical constraint in LLM deployments: managing long-horizon tasks within finite context windows. By modeling session history as a typed knowledge graph rather than flat text, TokenMizer achieves 50% smaller resume blocks while preserving architectural decisions and task rationale that traditional baselines lose.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers present the first comprehensive systems characterization of LLM agent memory architectures, introducing a taxonomy and profiling framework to analyze how different design choices impact performance across write and read paths. The study benchmarks ten representative systems and derives actionable recommendations for optimizing agent memory at scale.
AINeutralarXiv – CS AI · Jun 56/10
🧠A comprehensive survey examines safety mechanisms for embodied AI systems performing long-horizon robotic manipulation tasks, identifying critical gaps in current research across planning, policy design, and execution phases. The analysis reveals that while safety receives attention, evidence remains fragmented with limited formal guarantees, particularly for contact-rich manipulation scenarios in real-world deployment.
AINeutralarXiv – CS AI · Jun 36/10
🧠Researchers introduced DeskCraft, a new benchmark for evaluating AI desktop agents on complex, long-horizon professional workflows in creative and engineering software. The study reveals significant performance gaps, with GPT-4 achieving only 31.6% accuracy on standard tasks and 27.6% on interactive tasks requiring human collaboration, highlighting challenges in multi-step automation and proactive agent communication.
🧠 GPT-5
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce CoMIC, a cloud-edge framework that enables lightweight LLM agents on edge servers to handle long-horizon tasks by combining local execution with centralized cloud-based reflection and experience aggregation. The parameter-update-free approach improves performance across symbolic planning and text interaction tasks without requiring model fine-tuning.
AIBullisharXiv – CS AI · Jun 16/10
🧠Researchers introduce Adaptive Context Management (AdaCoM), an external LLM-based system that optimizes how AI agents handle long-context tasks by learning agent-specific compression strategies through reinforcement learning. The approach improves performance on web search and research benchmarks while avoiding the need to retrain frozen agents, revealing that high-performing agents benefit from preserving context fidelity while weaker agents need more aggressive compression.
AINeutralarXiv – CS AI · May 276/10
🧠Researchers introduce CARL, a hierarchical reinforcement learning algorithm that discovers reusable skills by exploiting local dynamics regularity—the observation that similar action sequences solve similar local transitions across different contexts. When integrated with existing HRL methods like HIQL, CARL demonstrates improved performance on complex tasks and meaningful skill clustering in humanoid environments.
AIBullisharXiv – CS AI · May 116/10
🧠AgentProg introduces a novel program-guided context management system for long-horizon GUI agents that addresses the critical bottleneck of expanding interaction history overhead. By reframing interaction history as structured programs with variables and control flow, the approach preserves semantic information while reducing context requirements, achieving state-of-the-art performance on AndroidWorld benchmarks while maintaining robustness on extended tasks.
AIBullisharXiv – CS AI · Feb 276/104
🧠Researchers have developed Hierarchy-of-Groups Policy Optimization (HGPO), a new reinforcement learning method that improves AI agents' performance on long-horizon tasks by addressing context inconsistency issues in stepwise advantage estimation. The method shows significant improvements over existing approaches when tested on challenging agentic tasks using Qwen2.5 models.
