CiteArk

Worth Reading Today

Focused on LLM and agent research, not popularity. Each day the Agent selects worthwhile new work from both themes, publishes inspectable Research Plans first, then keeps adding reproduction results.

1AgentsarXiv 2608.296220/4

AGENTIC R AG-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing

Xinke Jiang, Yue Fang, Zhibang Yang, Jiaran Gao, Zhixin Zhang, Tao Feng, Rihong Qiu, Wentao Zhang, Hongxin Ding, Ruizhe Zhang, Yongxin Xu, Yuheng Huang, Xu Chu, Junfeng Zhao, Yasha Wang

Why it is worth reading

The design may help agents revise misleading intermediate retrievals instead of accumulating them during long reasoning chains. This could benefit question-answering and research agents that need adaptive retrieval and memory control. Its value remains conditional on substantial training, judging, retrieval, checkpoint, and evaluator infrastructure that is not fixed in this compilation.

Core research claims

  • AGENTIC R AG-R1 reports higher or near-highest F1 than listed baselines across seven multi-hop, open-domain, and agentic QA benchmarks.
  • The paper reports increasing AGENTIC R AG-R1 F1 as the maximum reasoning-step budget grows on selected 2Wiki, Bamboogle, and TriviaQA evaluations.
  • The paper reports lower average inference time than TC-RAG and downstream results on MedQA, DeepResearch Bench, ALFWorld, and WebShop.
Artificial IntelligenceMachine Learning (cs.LG)Multiagent SystemsMachine Learning (stat.ML)
2Large language modelsarXiv 2608.295390/6

LoGo: Token-Level Dynamic Local-Global Attention

Yuqi Pan, Zheng Li, Bohao Tang, Zhen Qin, Guoqi Li

Why it is worth reading

If its reported conditions can be reproduced, LoGo could lower the cost of long-context language modeling by reserving full-context attention for tokens that appear to need distant information rather than applying it uniformly. This may help model builders serving long documents or retrieval-heavy prompts, while preserving ordinary local processing for predictable tokens. The value is conditional on the learned router, sparse kernels, training recipe, checkpoints, and evaluation data matching the paper; the fixed snapshot supplies none of the author implementation or in-house pretraining assets, so the claims remain unverified here.

Core research claims

  • The architecture ablation table reports that removing ContextNorm fails to converge, while additive fusion, auxiliary-loss budget control, and removing P-mask reduce the reported recall average relative to LoGo.
  • On the paper's 32k-checkpoint short-context recall aggregate, LoGo is reported as competitive with the other methods and scores 57.65 percentage points across six recall tasks.
  • In the controlled 1.5B comparison, LoGo reports the best language-modeling loss and Lambada perplexity among the listed full-attention and matched-budget static hybrid variants, with a higher commonsense-reasoning average than the full Transformer.
Computation and LanguageMachine Learning (cs.LG)Distributed, Parallel, and Cluster Computing