CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning
cs.AI
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/ATH-MaaS/Marco-DeepResearch
Terminology
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- A-MapReduce: Executing Wide Search via Agentic MapReduce
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
- CaStL: Constraints as Specifications through LLM Translation for Long-Horizon Task and Motion Planning
- Reasoning with Language Model is Planning with World Model
- VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications
- RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents
- An LLM Compiler for Parallel Function Calling
- DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking
- DeepAgent: A General Reasoning Agent with Scalable Toolsets
- TodoEvolve: Learning to Architect Agent Planning Systems
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks
- MiMo-V2-Flash Technical Report
- MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
- Mem-{\alpha}: Learning Memory Construction via Reinforcement Learning
- Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
- WideSearch: Benchmarking Agentic Broad Info-Seeking
- EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection