← Back to all news
arXiv AI By A. J. A. Jubayer Talukder, Mohammad Ariful Haque

When to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder

Read the original on arXiv AI →

The paper introduces a compact decoder that jointly handles gating and memory‑grounded hint generation for proactive assistants. Experiments on 28,058 decision points show that a single 1B‑parameter decoder can match or surpass two‑model pipelines, achieving higher precision and lower compute costs while preserving hint quality. Human evaluations confirm the benefit of memory grounding and demonstrate that the single‑model approach performs comparably to a larger 8B pipeline.

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 AI.

Related stories

arXiv Computation and Language
Oct 22

MemoProAgent: Toward Memory-Driven Proactive Assistance

MemoProAgent tackles memory‑driven proactive assistance by mining long‑horizon personal memories to decide when an assistant should intervene. The authors introduce MemoProBench, a benchmark pairing egocentric video with year‑long, distractor‑rich user memories and human‑verified trigger windows, and show that existing models perform poorly (≤15%). MemoProAgent uses a graph‑organized memory store and a lightweight RL stage to improve accuracy from <10% to 42.4% without training.

By Shenglai Zeng, Xiao Yang, Tiffany Ma, Xinyuan Zhang, Nanshu Wang, Deren Lei, Kai Sun, Xilun Chen, Tammy Stark, Xianhui Zhu, Yuetai Li, Rulin Shao, Tianxin Wei, Rakesh Wanga, Anuj Kumar, Jiliang Tang, Wen-tau Yih, Xin Luna Dong
llmsragreinforcement-learningbenchmarks
More like this →
arXiv Computation and Language
Oct 19

ProPerAgent: Toward Memory-Driven Proactive Assistance

The paper introduces ProPerMem, a benchmark for memory-driven proactive assistance that pairs egocentric video with long, distractor-rich personal memories and human-verified trigger windows. Baseline models perform poorly, achieving at most 15% accuracy, while an oracle-driven GPT-5.3-Chat model reaches 96% when given evidence inside the trigger window. Building on these insights, the authors develop ProPerAgent, a plug‑and‑play system that retrieves relevant memory from a graph store and uses lightweight reinforcement learning to improve proactive intervention accuracy to 42.4% without training.

By Shenglai Zeng, Xiao Yang, Tiffany Ma, Xinyuan Zhang, Nanshu Wang, Deren Lei, Kai Sun, Xilun Chen, Tammy Stark, Xianhui Zhu, Yuetai Li, Rulin Shao, Tianxin Wei, Rakesh Wanga, Anuj Kumar, Jiliang Tang, Wen-tau Yih, Xin Luna Dong
llmsragagentsreinforcement-learningbenchmarks
More like this →
arXiv AI
Sep 4

Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning

The paper introduces LRE (Learned Relevance Eviction), a lightweight, CPU‑only, language‑model‑free scorer that learns which parts of an agent’s interaction history are task‑critical and preserves them verbatim. In experiments, LRE matches or surpasses baseline eviction policies on accuracy‑cost trade‑offs, recovers 93% of full‑history accuracy, reduces worst‑case prompt size by 52%, and outperforms dense and token‑pruning encoders in conversational memory while being 295–1569× smaller. The method also achieves superior budgeted answer quality on LoCoMo reading and can be trained annotation‑free, recovering 95% of supervised scorer performance.

By Nusrat Jahan Lia, Aritra Mazumder
llmsagentsefficiency
More like this →