LLM Digest

Story

arxiv_cs_lg · May 29, 2026 · paper

Source brief

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

arxiv.orgMay 29, 2026
original source linked

In brief

Long-context reasoning remains a central challenge for large language models, which often fail to locate and integrate key information in extensive distracting content. Reinforcement learning with verifiable rewards (...

Read the original at arxiv.org →Open in live feed

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

Earlier in this thread 4 items

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Selector-Guided Autonomous Curriculum for One-Shot Reinforcement Learning from Verifiable Rewards

Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates

KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference