LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! Paper • 2502.07374 • Published 7 days ago • 30
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published 8 days ago • 84
Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation Paper • 2502.00306 • Published 17 days ago • 4
Lifelong Sequential Knowledge Editing without Model Degradation Paper • 2502.01636 • Published 15 days ago • 5
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning Paper • 2502.01100 • Published 15 days ago • 15
SRMT: Shared Memory for Multi-agent Lifelong Pathfinding Paper • 2501.13200 • Published 27 days ago • 63
AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents Paper • 2407.04363 • Published Jul 5, 2024 • 28
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback Paper • 2501.10799 • Published about 1 month ago • 15
Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models Paper • 2501.13629 • Published 26 days ago • 44
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation Paper • 2412.06531 • Published Dec 9, 2024 • 71
POGEMA: A Benchmark Platform for Cooperative Multi-Agent Navigation Paper • 2407.14931 • Published Jul 20, 2024 • 22
Complexity of Symbolic Representation in Working Memory of Transformer Correlates with the Complexity of a Task Paper • 2406.14213 • Published Jun 20, 2024 • 21
BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack Paper • 2406.10149 • Published Jun 14, 2024 • 49