Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?

• URL: http://arxiv.org/abs/2605.30152v1
• Date: Thu, 28 May 2026 16:10:32 GMT
• Title: Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?
• Abstract summary: Proactive agents read user activity as text and call an LLM on every event to decide whether to act.<n>We treat the always-on signal as graph updates rather than text.<n>One forward pass yields a per-event trigger probability and a per-entity routing score.
• Score: 36.54616681758304
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Proactive agents read user activity as text and call an LLM on every event to decide whether to act. But user activity is not natively text: it is a structured event stream of (actor, verb, object, timestamp) tuples that the operating system already maintains in graph form. Rendering the structure as text and asking an LLM to recover it is a round-trip the system never had to take. We treat the always-on signal as graph updates rather than text and use a small temporal-graph-learning (TGL) model as the encoder: one forward pass yields a per-event trigger probability and a per-entity routing score, and only the downstream agent (turning a small structured handoff into a fluent user-facing sentence) is an LLM call, invoked only when the trigger fires. TGL improves F1 on each of 14 backbones (mean +16.7, up to +46.0); in trigger-architecture comparisons, one TGL checkpoint gives the strongest trigger AUCs and the most stable deployed threshold. It runs at 11.13 ms per event on a GPU server and 13.99 ms on a consumer laptop, approximately 4--7x and 12--83x faster than every single-forward LLM-as-trigger configuration tested in each regime, with an approximately 220 MiB BF16 resident footprint deployable on-device alongside the privacy-sensitive activity stream it consumes.

Related papers

• STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition [4.078975699391066]
  We present STELLA, an efficient sensor-to-LLM translation framework for on-device HAR.<n>A lightweight hierarchical tokenizer compresses an entire multi-channel inertial window into a fixed set of compact latent sensor tokens.<n> STELLA supports on-device personalization, adapting only the lightweight tokenizer on small amounts of user-specific labelled data.
  arXiv  Detail & Related papers  (2026-07-03T08:21:40Z)
• ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents [61.184954205350984]
  ClawArena-Team is a benchmark of 41 multi-turn, multimodal, multi-agent scenarios spanning 258 evaluation rounds and 72 staged updates.<n>All scoring is execution-based with no LLM judge: an overall score -- the Subagent-Management Score (SMS) -- multiplies task correctness by a least-privilege and modality-routing factor.
  arXiv  Detail & Related papers  (2026-06-30T06:06:08Z)
• ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories [18.739245125968175]
  Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution--properties absent from existing datasets.<n>We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm that addresses these gaps jointly.
  arXiv  Detail & Related papers  (2026-06-09T23:44:26Z)
• Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents [2.417342411475111]
  Nautilus Compass is a black-box drift detector and agent memory layer for production coding agents.<n>The system ships as a Claude Code plugin, an MCP 20245 A2A server, a CLI, and an API on one daemon.
  arXiv  Detail & Related papers  (2026-05-11T01:49:17Z)
• GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0) [56.81743709880371]
  Long-horizon large language model (LLM) agents are fundamentally limited by context.<n>We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget.<n>We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: information density and context.
  arXiv  Detail & Related papers  (2026-04-18T17:59:15Z)
• Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines [0.7551404527457958]
  We describe a new agentic serving system that efficiently schedules arbitrary multi-LLM agentic onto a GPU cluster.<n>Scepsy achieves up to 2.4x higher throughput and 27x lower latency compared to systems that optimize LLMs independently.
  arXiv  Detail & Related papers  (2026-04-16T16:15:29Z)
• Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights [75.83625828306839]
  textbfDrag-and-Drop LLMs (textitDnD) eliminates per-task training by mapping a handful of unlabeled task prompts directly to LoRA weight updates.<n>A lightweight text encoder distills each prompt batch into condition embeddings, which are then transformed by a cascaded hyper-convolutional decoder into the full set of LoRA matrices.
  arXiv  Detail & Related papers  (2025-06-19T15:38:21Z)
• LLM-AutoDiff: Auto-Differentiate Any LLM Workflow [58.56731133392544]
  We introduce LLM-AutoDiff: a novel framework for Automatic Prompt Engineering (APE)<n>LLMs-AutoDiff treats each textual input as a trainable parameter and uses a frozen backward engine to generate feedback-akin to textual gradients.<n>It consistently outperforms existing textual gradient baselines in both accuracy and training cost.
  arXiv  Detail & Related papers  (2025-01-28T03:18:48Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• SAGE: Smart home Agent with Grounded Execution [1.5256015470528725]
  SAGE (Smart Home Agent with Grounded Execution) overcomes limitations by using a scheme in which a user request triggers an LLM-controlled sequence of discrete actions. These actions can be used to retrieve information, interact with the user, or manipulate device states. We introduce a benchmark of 50 new and challenging smart home tasks where SAGE achieves a 75% success rate.
  arXiv  Detail & Related papers  (2023-11-01T18:36:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.