Robin Williams PRO

bfuzzy1's activity

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

upvoted a paper 1 day ago

Agentless: Demystifying LLM-based Software Engineering Agents

Paper • 2407.01489 • Published Jul 1, 2024 • 56

upvoted 3 papers 2 days ago

Agent Laboratory: Using LLM Agents as Research Assistants

Paper • 2501.04227 • Published 6 days ago • 72

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though

Paper • 2501.04682 • Published 5 days ago • 75

Entropy-Guided Attention for Private LLMs

Paper • 2501.03489 • Published 7 days ago • 12

upvoted a collection 4 days ago

LLM Reasoning Papers

Collection

Papers to improve reasoning capabilities of LLMs • 18 items • Updated 4 days ago • 99

upvoted 14 papers 5 days ago

HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation

Paper • 2412.21199 • Published 14 days ago • 11

Training Software Engineering Agents and Verifiers with SWE-Gym

Paper • 2412.21139 • Published 14 days ago • 20

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Paper • 2412.21187 • Published 14 days ago • 34

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Paper • 2412.19723 • Published 17 days ago • 78

Dynamic Scaling of Unit Tests for Code Reward Modeling

Paper • 2501.01054 • Published 12 days ago • 16

CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings

Paper • 2501.01257 • Published 12 days ago • 46

SDPO: Segment-Level Direct Preference Optimization for Social Agents

Paper • 2501.01821 • Published 11 days ago • 18

Graph Generative Pre-trained Transformer

Paper • 2501.01073 • Published 12 days ago • 17

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

Paper • 2501.03124 • Published 7 days ago • 13

Scaling Laws for Floating Point Quantization Training

Paper • 2501.02423 • Published 9 days ago • 24

Test-time Computing: from System-1 Thinking to System-2 Thinking

Paper • 2501.02497 • Published 9 days ago • 34

Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback

Paper • 2501.03916 • Published 6 days ago • 14

REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models

Paper • 2501.03262 • Published 10 days ago • 74

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning

Paper • 2501.03226 • Published 7 days ago • 34

upvoted a paper 7 days ago

BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery

Paper • 2501.01540 • Published 11 days ago • 6