Aamer Mihaysi

O96a's activity

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

commented a paper about 21 hours ago

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

Paper • 2607.18754 • Published 2 days ago • 21 •

4

commented a paper 2 days ago

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

Paper • 2607.07820 • Published 15 days ago • 86 •

4

commented a paper 3 days ago

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

Paper • 2607.11683 • Published 10 days ago • 139 •

4

commented a paper 4 days ago

Rethinking the Evaluation of Harness Evolution for Agents

Paper • 2607.12227 • Published 9 days ago • 9 •

3

commented a paper 5 days ago

Spectral Rewiring for Exploration, Purification, and Model Merging

Paper • 2607.03065 • Published 20 days ago • 25 •

5

commented a paper 6 days ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published 7 days ago • 195 •

3

commented a paper 7 days ago

From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization

Paper • 2607.07702 • Published 15 days ago • 11 •

3

commented a paper 8 days ago

Multi-Agent LLMs Fail to Explore Each Other

Paper • 2607.11250 • Published 10 days ago • 16 •

4

commented a paper 9 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 15 days ago • 135 •

3

commented a paper 10 days ago

KronQ: LLM Quantization via Kronecker-Factored Hessian

Paper • 2607.07964 • Published 15 days ago • 32 •

4

commented a paper 11 days ago

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

Paper • 2607.08716 • Published 14 days ago • 14 •

6

commented a paper 12 days ago

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Paper • 2601.16211 • Published 21 days ago • 54 •

3

commented a paper 13 days ago

A Quantized Native Runtime for On-Device Semantic Audio Generation

Paper • 2607.08526 • Published 14 days ago • 4 •

4

commented a paper 14 days ago

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Paper • 2607.01232 • Published 21 days ago • 6 •

3

commented a paper 15 days ago

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration

Paper • 2607.05465 • Published 17 days ago • 12 •

3

commented a paper 16 days ago

KVpop -- Key-Value Cache Compression with Predictive Online Pruning

Paper • 2607.05061 • Published 17 days ago • 24 •

3

commented a paper 17 days ago

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

Paper • 2607.01804 • Published 21 days ago • 31 •

4

commented a paper 19 days ago

AutoMem: Automated Learning of Memory as a Cognitive Skill

Paper • 2607.01224 • Published 22 days ago • 21 •

3

commented a paper 20 days ago

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Paper • 2607.02255 • Published 21 days ago • 64 •

3

commented a paper 21 days ago

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

Paper • 2607.00466 • Published 22 days ago • 32 •

3