Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
Paper • 2607.28074 • Published • 9
siyeng feng
siyengfeng
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale upvoted a paper 3 days ago
Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability upvoted a paper 3 days ago
Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent SystemsOrganizations
None yet
upvoted a paper 2 days ago
upvoted 12
papers 3 days ago
Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
Paper • 2607.26637 • Published • 8
Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
Paper • 2607.27958 • Published • 12
MemHarness: Memory Is Reconstructed, Not Replayed
Paper • 2607.28272 • Published • 14
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
Paper • 2607.27919 • Published • 49
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
Paper • 2607.28568 • Published • 168
Metis: Memory Foundation Model
Paper • 2607.26760 • Published • 259
Memory for Large Language Models
Paper • 2607.25380 • Published • 9
Can AI agents conduct open-ended AI research? Early evidence from two case studies
Paper • 2607.27191 • Published • 16
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
Paper • 2607.25659 • Published • 80
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Paper • 2607.25308 • Published • 39
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
Paper • 2607.26784 • Published • 25
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
Paper • 2607.25675 • Published • 61
upvoted 7
papers 4 days ago
Building to the Test: Coding Agents Deliver What You Check, Not What You Requested
Paper • 2606.28430 • Published • 9
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
Paper • 2607.00152 • Published • 9
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?
Paper • 2607.01211 • Published • 9
MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
Paper • 2607.01071 • Published • 31
Pass the Baton: Trajectory-Relayed On-Policy Distillation
Paper • 2607.26057 • Published • 31
Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory
Paper • 2607.24368 • Published • 31
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents
Paper • 2607.25431 • Published • 103