Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Paper • 2605.05242 • Published • 123
ℏεsam PRO
hesamation
AI & ML interests
post-training / reasonign models / RAG
Recent Activity
upvoted a paper about 1 month ago
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction new activity about 2 months ago
hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled:question: which version of Opus-Reasoning-Distilled? new activity about 2 months ago
hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF:Model frequently enters repetitive output loops”Organizations
upvoted a paper about 1 month ago
question: which version of Opus-Reasoning-Distilled?
3
#1 opened about 2 months ago
by 
recallmenot
New activity in hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF about 2 months ago
Model frequently enters repetitive output loops”
👍 2
2
#5 opened about 2 months ago
by 
Arkovski
Minisforum ms-s1 max mini pc (Strix Halo)
🔥 1
1
#2 opened about 2 months ago
by 
billmeyer
liked a
model about 2 months ago
updated a
collection about 2 months ago
upvoted a collection about 2 months ago
When will there be .gguf model files?
1
#3 opened about 2 months ago
by 
Kociol
liked a
model about 2 months ago
updated 2
models about 2 months ago
published a
model about 2 months ago
liked a
model about 2 months ago
published a
model about 2 months ago
upvoted a paper 3 months ago
upvoted 3
papers 5 months ago
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
Paper • 2601.05593 • Published • 87
BabyVision: Visual Reasoning Beyond Language
Paper • 2601.06521 • Published • 201
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
Paper • 2601.06943 • Published • 214
upvoted an article 5 months ago
Article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
NormalUhr
• • 126 upvoted an article 6 months ago
Article
We Got Claude to Fine-Tune an Open Source LLM
burtenshaw, evalstate
• • 629