StoryReward, trained on a new 100k story preference dataset, sets state-of-the-art performance on the introduced StoryRMB benchmark for aligning LLM stories with human preferences.
Qwenlong-l1: Towards long-context large reasoning models with reinforcement learning
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
OPSDL improves long-context LLM performance by having the model self-distill from its short-context capability using point-wise reverse KL divergence on generated tokens, outperforming SFT and DPO on benchmarks without harming short-context abilities.
MemAgent uses multi-conversation RL to train a memory agent that reads text in segments and overwrites memory, extrapolating from 8K training to 3.5M token QA with under 5% loss and 95%+ on 512K RULER.
Combines GRPO with teacher-guided on-policy distillation and introduces LongBlocks dataset to yield more stable long-context reasoning than either method alone.
LongAct uses saliency from high-magnitude activations to guide sparse weight updates in long-context RL, yielding about 8% gains on LongBench v2 across multiple algorithms.
Decomposing long-context reasoning into atomic skills, synthesizing targeted pseudo-datasets, and applying RL improves LLM performance on long-context benchmarks by an average of 7.7%.
GLM-4.5, a 355B-parameter MoE model with hybrid reasoning, scores 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified while ranking 3rd overall and 2nd on agentic benchmarks.