ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence
Paper • 2610.34283 • Published • 40
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence upvoted a paper 12 days ago
Harness-Model Collaboration for Long-Horizon Continual Learning upvoted a paper 12 days ago
SearchHorizonBench: A Benchmark for Search Value in AI AgentsOrganizations
None yet
upvoted a paper 10 days ago
upvoted 7
papers 12 days ago
Harness-Model Collaboration for Long-Horizon Continual Learning
Paper • 2610.34724 • Published • 12
SearchHorizonBench: A Benchmark for Search Value in AI Agents
Paper • 2610.34714 • Published • 9
What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents
Paper • 2610.34491 • Published • 22
Memory Tax: Dissecting the Net Value of Agent Memory
Paper • 2610.34073 • Published • 27
Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
Paper • 2610.32046 • Published • 22
RSI Arena: Towards Recursive Self-Improvement with Human Feedback
Paper • 2610.33624 • Published • 26
HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory
Paper • 2610.24520 • Published • 32
upvoted 7
papers 17 days ago
VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents
Paper • 2610.28679 • Published • 14
Which Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams
Paper • 2610.27227 • Published • 11
Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures
Paper • 2610.28887 • Published • 18
DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents
Paper • 2610.19376 • Published • 21
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
Paper • 2610.30755 • Published • 23
Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models
Paper • 2610.25100 • Published • 48
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
Paper • 2610.30949 • Published • 100
upvoted 3
papers 27 days ago
One Model to Loop Them All: Elastic Latent Recurrence for Language Models
Paper • 2610.12582 • Published • 13
Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
Paper • 2610.12341 • Published • 39
Thinking Inertia: LLMs Keep Thinking When Told Not To
Paper • 2610.11765 • Published • 127
upvoted 2
papers about 1 month ago