Aamer Mihaysi

O96a's activity

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

commented a paper about 5 hours ago

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

Paper • 2608.03796 • Published 7 days ago • 9 •

2

commented a paper 1 day ago

DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces

Paper • 2608.03451 • Published 7 days ago • 30 •

4

commented a paper 2 days ago

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

Paper • 2608.05784 • Published 5 days ago • 24 •

6

commented a paper 3 days ago

Invisible Shortcuts: Why Vision Encoders Know Your Camera

Paper • 2608.05424 • Published 6 days ago • 16 •

3

commented a paper 4 days ago

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Paper • 2608.05013 • Published 7 days ago • 34 •

3

commented a paper 5 days ago

ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?

Paper • 2608.03874 • Published 7 days ago • 14 •

4

commented a paper 6 days ago

DAPD: Dual-Anchored Policy Distillation

Paper • 2608.01735 • Published 8 days ago • 108 •

4

commented a paper 7 days ago

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

Paper • 2607.26611 • Published 13 days ago • 32 •

3

commented a paper 11 days ago

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

Paper • 2607.25675 • Published 14 days ago • 65 •

3

commented a paper 12 days ago

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

Paper • 2607.24223 • Published 15 days ago • 94 •

6

commented a paper 13 days ago

Codifying the Judge: Scalable Evaluation via Program Distillation

Paper • 2607.22561 • Published May 29 • 8 •

3

commented a paper 14 days ago

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

Paper • 2607.21503 • Published 19 days ago • 28 •

4

commented a paper 15 days ago

Sample-Efficient Learning from Agent Experience

Paper • 2607.21051 • Published 19 days ago • 19 •

4

commented a paper 16 days ago

OpenForgeRL: Train Harness-native Agents in Any Environment

Paper • 2607.21557 • Published 19 days ago • 9 •

4

commented a paper 17 days ago

LLMs Get Lost in Evolving User Intent

Paper • 2607.20734 • Published 20 days ago • 24 •

4

commented a paper 18 days ago

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

Paper • 2607.19747 • Published 20 days ago • 30 •

6

commented a paper 19 days ago

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

Paper • 2607.18754 • Published 21 days ago • 25 •

4

commented a paper 20 days ago

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

Paper • 2607.07820 • Published Jul 8 • 92 •

4

commented a paper 21 days ago

RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM

Paper • 2607.11683 • Published 29 days ago • 148 •

4

commented a paper 22 days ago

Rethinking the Evaluation of Harness Evolution for Agents

Paper • 2607.12227 • Published 28 days ago • 10 •

3