Tag
ConvMem is a training-free, parallelizable framework that reformulates long-context reasoning in large language models as hierarchical convolution to improve efficiency, avoid overfitting, and outperform baseline methods.
This paper presents SimpleOPD, a method for on-policy distillation from long-context reasoning teachers to short-context students, overcoming tokenizer mismatch and training instability to enhance mathematical reasoning capabilities.
This paper introduces Decentralized Language Models (DeLM), a framework for multi-agent systems that uses parallel agents with a shared verified context to improve test-time scaling and reduce costs, achieving state-of-the-art results on SWE-bench Verified and LongBench-v2.
LongTraceRL introduces tiered distractor construction and rubric reward design to improve long-context reasoning in language models using reinforcement learning. The method generates multi-hop questions via knowledge graph random walks and uses search agent trajectories to build challenging distractors, with a rubric reward providing entity-level process supervision.
MemReread introduces a method for long-context reasoning that avoids intermediate retrieval by decomposing questions and rereading text to recover discarded information, achieving linear time complexity. It outperforms baseline frameworks on long-context reasoning tasks.