arXiv Computation and Language September 24, 2026 By Yingrui Li, Han Chen

When Learned Context Planning Fails to Beat Strong Retrieval: A Controlled Study of Planning, Routing, and Reranking for Long-Context QA

Read the original on arXiv Computation and Language →

The study evaluates whether learned context planning can outperform strong retrieval methods in long-context multiple-choice question answering. Using 503 LongBench-v2 MCQ questions and a Qwen2.5-7B-Instruct model, the planner—trained on outcome-selected traces—achieves lower accuracy than anchored hybrid retrieval and BM25 across various character budgets. Even with tight budgets, the planner only marginally improves or matches retrieval, indicating that learned planning provides a weak relevance signal rather than a replacement for robust retrieval.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

4d ago

Learning to Retrieve Missing Evidence for Long-Term Memory QA

arXiv:2609.37443v1 Announce Type: cross Abstract: Long-term memory enables language models to use past interactions in future conversations. However, evidence needed to answer a question may be scatt...

By Yi-Xuan Deng, Yi Zhang, Wei Liu, Chao Xue, Shuojin Yang

llms reinforcement-learning

arXiv Computation and Language

Aug 25

DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation

DynaKRAG is a unified framework that learns a state‑conditioned policy to control evidence acquisition in multi‑hop retrieval‑augmented generation. It uses a deterministic validity layer to build an action set, a learned continuation gate to decide between generating an answer or gathering more evidence, and an advantage scorer to rank evidence operations by predicted gain. Across HotpotQA, 2Wiki, and MuSiQue with various backbone models, DynaKRAG achieves top EM and F1 scores, improves token and retrieval efficiency, and enables terminal evidence compression that reduces context size while boosting answer quality.

By Chenyu Zhou, Yaqi Wu, Xiaolei Guo, Jiaqi Huang, Xianfa Zhang, Junxu Zhang, Zhuo Yu, Zhubo Shi, Jianghao Lin, Dongdong Ge

llms rag

Hugging Face Trending Papers

Jul 28

Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs

Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation. We investigate whether verbalized confidence from black-box language models can serve as an actionable signal for retrieval routing.

llms rag nlp benchmarks

arXiv AI

Jul 29

Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs

arXiv:2607. 25600v1 Announce Type: cross Abstract: Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation.

By Chandan Kumar Sah, Xiaoli Lian, Li Zhang

llms rag nlp benchmarks

arXiv AI

Aug 14

ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval

arXiv:2608. 12720v1 Announce Type: cross Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely treated as evolvable components.

By Haolong Chen, Liang Zhang, Zhuo Li, Lei Xue, Guanrxu Zhu

llms agents benchmarks

arXiv AI

Jul 13

Self-Guided Test-Time Training for Long-Context LLMs

arXiv:2607. 09415v1 Announce Type: cross Abstract: Long-context processing has become increasingly important for large language models (LLMs), but simply extending the context window does not guarantee effective utilization of long inputs.

By Xinyu Zhu, Zhe Xu, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Kaushik Rangadurai, Hua Zhi, Frank Shyu, Sandeep Pandey, Luke Simon, Yu Meng, Xi Liu

llms benchmarks

One email a morning, machine-written

Related stories

Learning to Retrieve Missing Evidence for Long-Term Memory QA

DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation

Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs

Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs

ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval

Self-Guided Test-Time Training for Long-Context LLMs