Aamer Mihaysi

O96a's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper about 19 hours ago

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

Paper • 2608.12123 • Published 2 days ago • 2 •

3

commented 3 papers 2 days ago

Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents

Paper • 2608.08389 • Published 5 days ago • 12 •

3

Business Arena: Benchmarking LLM Agents in a Realistic Marketplace

Paper • 2608.08621 • Published 5 days ago • 20 •

5

Omega-S: A Functional Resilience Index for LLM Fine-Tuning

Paper • 2608.03887 • Published 10 days ago • 7 •

4

commented a paper 3 days ago

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 4 days ago • 97 •

3

commented 2 papers 4 days ago

Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression

Paper • 2608.04569 • Published 9 days ago • 12 •

3

Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss

Paper • 2608.03796 • Published 10 days ago • 14 •

4

commented a paper 5 days ago

DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces

Paper • 2608.03451 • Published 10 days ago • 33 •

4

commented a paper 6 days ago

Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay

Paper • 2608.05784 • Published 8 days ago • 28 •

6

commented a paper 7 days ago

Invisible Shortcuts: Why Vision Encoders Know Your Camera

Paper • 2608.05424 • Published 9 days ago • 17 •

3

commented a paper 8 days ago

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Paper • 2608.05013 • Published 10 days ago • 35 •

3

commented a paper 9 days ago

ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?

Paper • 2608.03874 • Published 10 days ago • 14 •

4

commented a paper 10 days ago

DAPD: Dual-Anchored Policy Distillation

Paper • 2608.01735 • Published 11 days ago • 147 •

4

commented a paper 11 days ago

Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants

Paper • 2607.26611 • Published 16 days ago • 32 •

3

commented a paper 15 days ago

DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space

Paper • 2607.25675 • Published 17 days ago • 67 •

3

commented a paper 16 days ago

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Paper • 2607.24223 • Published 18 days ago • 95 •

6

commented a paper 17 days ago

Codifying the Judge: Scalable Evaluation via Program Distillation

Paper • 2607.22561 • Published May 29 • 8 •

3

commented a paper 18 days ago

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

Paper • 2607.21503 • Published 22 days ago • 28 •

4

commented a paper 19 days ago

Sample-Efficient Learning from Agent Experience

Paper • 2607.21051 • Published 22 days ago • 20 •

4

commented a paper 20 days ago

OpenForgeRL: Train Harness-native Agents in Any Environment

Paper • 2607.21557 • Published 22 days ago • 10 •

4