Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
Paper
•
2602.02477
•
Published
•
7
M Saad Salman
MSS444
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
upvoted
a
paper
1 day ago
LoopViT: Scaling Visual ARC with Looped Transformers
Organizations
None yet
upvoted
17
papers
1 day ago
LoopViT: Scaling Visual ARC with Looped Transformers
Paper
•
2602.02156
•
Published
•
10
Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
Paper
•
2602.01511
•
Published
•
12
RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
Paper
•
2602.02486
•
Published
•
14
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
Paper
•
2602.01058
•
Published
•
38
Kimi K2.5: Visual Agentic Intelligence
Paper
•
2602.02276
•
Published
•
190
SimpleGPT: Improving GPT via A Simple Normalization Strategy
Paper
•
2602.01212
•
Published
•
2
Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation
Paper
•
2602.03806
•
Published
•
4
LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents
Paper
•
2602.01053
•
Published
•
6
Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
Paper
•
2602.00747
•
Published
•
8
Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
Paper
•
2602.03216
•
Published
•
11
Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification
Paper
•
2601.21244
•
Published
•
12
No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs
Paper
•
2602.02103
•
Published
•
61
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
Paper
•
2602.03411
•
Published
•
33
SWE-World: Building Software Engineering Agents in Docker-Free Environments
Paper
•
2602.03419
•
Published
•
36
MARS: Modular Agent with Reflective Search for Automated AI Research
Paper
•
2602.02660
•
Published
•
52
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Paper
•
2602.01785
•
Published
•
84
upvoted
3
papers
2 days ago
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
Paper
•
2601.22588
•
Published
•
4
Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning
Paper
•
2602.00759
•
Published
•
5
PromptRL: Prompt Matters in RL for Flow-Based Image Generation
Paper
•
2602.01382
•
Published
•
8