Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Paper • 2610.01415 • Published • 71
Zhi Zheng
zz1358m
AI & ML interests
LLM reasoning, Trustworthy LLM, LLM application, Neural combinatorial optimization.
Recent Activity
upvoted a paper 1 day ago
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States upvoted a paper 1 day ago
Agent Priors-guided Policy Learning authored a paper 12 days ago
GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent SkillsOrganizations
upvoted 2
papers 1 day ago
upvoted a paper 12 days ago
upvoted a paper 18 days ago
upvoted 3
papers about 1 month ago
Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO
Paper • 2608.27351 • Published • 22
Best Practice Critic Optimization
Paper • 2608.23566 • Published • 18
Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
Paper • 2608.17310 • Published • 110
upvoted a collection about 2 months ago
upvoted 6
papers 4 months ago
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
Paper • 2605.19282 • Published • 9
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
Paper • 2606.06036 • Published • 78
Inference-Time Attribute Distribution Alignment for Unconditional Diffusion
Paper • 2605.07456 • Published • 2
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Paper • 2606.13681 • Published • 146
One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA
Paper • 2606.10572 • Published • 17
Why Muon Outperforms Adam: A Curvature Perspective
Paper • 2606.04662 • Published • 10
upvoted a paper 8 months ago