PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory

Zhifei Xie; Zongzheng Hu; Fangda Ye; Xin Zhang; Haobo Chai; Zihang Liu; Pengcheng Wu; Guibin Zhang

Figure 2: Illustration of the proposed DD-MM-PAS, a potentially general paradigm for proactive AI, alongside its diverse application instances. The framework is composed of three interconnected modules: Demand Detecting (DD) acts as the proactive engine to predict latent human needs from real-time signals; the Memory Module (MM) accumulates persistent, long-term data to enable deep, person-level understanding; and the Proactive Agent System (PAS) serves as the system backbone, managing real-time execution, information fusion, and memory scheduling. Together, these components transition AI from a passive, query-based responder into an active initiator of assistance across professional, academic, and daily contexts.

Figure 3: IntentFlow model architecture for streaming information–based human deep intent reasoning and demand detection. The system processes textual information fragments from the frontend and predicts one control token per step: <silent> (wait for the next message), <fast intervention> (low-latency understanding help, e.g., concept explanation, typically <1 s), or <full assistance> (invoke memory modules and global context for deep intent detection.

Figure 4: Different DD outcomes trigger different system modes: <silent> avoids unnecessary interruption, <fast intervention> provides immediate help, and <full assistance> enables agentic operations for higher-quality support.

Figure 5: Overview of the LatentNeeds dataset and benchmark composition, showing the distribution across three major domains (meetings, learning, and daily life) and their corresponding subcategories. The middle part summarizes the data construction pipeline, including public-data grounding, multi-agent information-stream generation, iterative human-intent generation, structured reformatting, and AI-based post-filtering, together with the collection and refinement of real-world sessions. The bottom part outlines the training strategy: separate supervised fine-tuning of the Demand Detector and MemLoader, followed by joint reinforcement learning for deeper human-intent alignment.

Figure 6: Overview of the internal architecture of Pask-MM . Inspired by hierarchical memory designs in modern agent systems, the framework organizes memory into three functional components with different access frequencies: user memory

\mathcal{M}_{\text{user}}

, workspace memory

\mathcal{M}_{\text{wsp}}

, and global memory

\mathcal{M}_{\text{global}}

.

\mathcal{M}_{\text{user}}

stores stable user profiles for personalization,

\mathcal{M}_{\text{wsp}}

maintains short-term session dynamics for real-time inference, and

\mathcal{M}_{\text{global}}

records long-term episodic knowledge for retrieval and validation. During interaction, workspace memory is updated continuously to support low-latency reasoning, while

\mathcal{M}_{\text{user}}

and

\mathcal{M}_{\text{global}}

evolve only after session completion through offline maintenance and compression.

Figure 7: System architecture of Pask-PAS , illustrating how frontend devices, server infrastructure, and AI backends form an always-on loop for perception, understanding, and proactive action.

Figure 8: Balanced accuracy as a function of conversation depth. Turns are grouped into non-overlapping buckets of 4 consecutive turns (1–4, 5–8, …, 57–60). (a) Per-bucket accuracy: each point is the balanced average of demand recall and non-demand precision within that bucket alone, revealing local fluctuations. (b) Cumulative accuracy: each point aggregates all turns from the start up to and including the current bucket, yielding a smoothed view of overall degradation. IntentFlow maintains

>

80% balanced accuracy across all buckets, while the strongest baseline (Gemini-3-Flash) drops from 85.6 to 70.8 (

\Delta

=–17.3%).

Model	Type	Work				Learning			Daily			Overall
		Business	Product	Tech	Work	STEM	Program.	Human.	Personal	Tools &	Content
		Metrics	Strategy	Engineer.	Collab.	Lecture	Tutorial	Business	Life	Workflow	Knowl.
GPT-5-Mini	Demand.	71.1	69.1	73.2	65.8	78.3	60.3	69.5	63.4	67.3	46.5	66.5
	No-Dem.	88.8	92.5	83.7	76.8	79.2	91.2	91.7	91.2	93.8	90.6	88.0
	Avg.	79.9	80.8	78.5	71.3	78.8	75.8	80.6	77.3	80.5	68.5	77.2
GPT-5-Nano	Demand.	80.5	87.4	88.4	77.2	58.0	53.4	51.6	77.5	74.4	63.1	71.2

Table 1: Main results on the IntentFlow Proactive Demand Detection Benchmark. Each cell reports the turn-level accuracy score (0–100). Demand = accuracy on demand turns; No-Dem. = accuracy on non-demand turns; Avg. = balanced average (1:1 demand/non-demand). Columns are grouped by domain: Work (Business Metrics, Product Strategy, Tech Engineer., Work Collab.), Learning (STEM Lecture, Program. Tutorial, Human. Business), Daily (Personal Life, Tools & Workflow, Content & Knowl.). Bold = best per column; Italic = second best.

Model	Demand	Work				Learning			Daily			Overall
		Business	Product	Tech	Work	STEM	Program.	Human.	Personal	Tools &	Content
		Metrics	Strategy	Engineer.	Collab.	Lecture	Tutorial	Business	Life	Workflow	Knowl.
GPT-5-Mini	Req.	72.9	71.6	71.0	66.9	100.0	49.1	33.3	60.7	67.8	47.8	64.1
	Ins.	65.9	60.3	83.3	63.5	75.6	70.5	70.7	65.1	64.0	46.4	66.5
	Avg.	69.4	65.9	77.2	65.2	87.8	59.8	52.0	62.9	65.9	47.1	65.3
GPT-5-Nano	Req.	80.5	87.0	88.9	76.2	68.8	50.9	33.3	80.4	77.6	60.9	70.5

Table 2: Performance by demand type on the IntentFlow benchmark. Each cell reports the turn-level accuracy score (0–100) on demand turns only. Req. = Requirement-type demands (decision support, task planning, problem solving, summarization, information lookup); Ins. = Insight-type demands (risk warning, knowledge gap, callback reminder, context synthesis, trend insight, sentiment analysis). Bold = best per column; Italic = second best.

Model	Type	Turn Position (bucket)															$\Delta$ (%)
Model	Type	1-4	5-8	9-12	13-16	17-20	21-24	25-28	29-32	33-36	37-40	41-44	45-48	49-52	53-56	57-60	$\Delta$ (%)
GPT-5-Mini	Demand.	80.3	76.6	74.7	68.4	69.3	67.2	67.7	64.5	60.2	67.0	65.4	59.4	60.0	50.9	51.0	-36.5
	No-Dem.	93.1	92.7	86.3	87.9	82.8	90.5	84.2	85.5	89.1	87.2	83.6	91.4	86.7	95.6	89.6	-3.8
	Avg.	86.7	84.6	80.5	78.1	76.0	78.9	76.0	75.0	74.7	77.1	74.5	75.4	73.4	73.2	70.3	-19.0
GPT-5-Nano	Demand.	88.6	78.6	82.0	80.9	67.5	69.0	66.1	69.1	71.0	75.5	66.7	76.8	70.8	75.4	60.8	-31.4
	No-Dem.	75.2	68.8	77.2	73.1	71.1	71.6	71.1	73.1	69.6	67.5	70.9	68.8	74.7	72.1	77.1	2.5

Table 3: Per-turn-bucket performance under the multi-turn setting. Turn positions are grouped into buckets of 4 consecutive turns. Demand = accuracy on demand turns; No-Dem. = accuracy on non-demand turns; Avg. = balanced average.

\Delta

(%) = relative change from first to last bucket. Bold = best per column; Italic = second best.

Model

Per-Turn Latency (ms)

T

=1–12

T

=13–24

T

=25–36

T

=37–48

T

=49–60

Dem.

N-D.

Avg.

Dem.

N-D.

Avg.

Dem.

N-D.

Avg.

Dem.

N-D.

Avg.

Dem.

N-D.

Avg.

GPT-5-Mini

10.4k

6.7k

8.1k

10.2k

7.1k

8.4k

9.9k

7.3k

8.4k

9.3k

6.4k

7.6k

8.6k

5.8k

7.1k

GPT-5-Nano

7.4k

6.3k

6.7k

6.9k

5.7k

6.2k

7.0k

6.2k

6.5k

7.2k

6.2k

6.6k

6.3k

5.8k

6.0k

GPT-oss-120b

7.7k

6.3k

6.8k

8.3k

6.6k

7.3k

9.1k

8.4k

8.7k

7.9k

6.8k

7.3k

8.6k

7.4k

8.0k

Gemini-3-Flash

3.6k

3.0k

3.2k

3.9k

3.7k

3.8k

4.3k

4.1k

4.2k

4.3k

4.4k

4.3k

4.4k

Table 4: Per-turn inference latency by conversation position. Turn positions are grouped into buckets of 12 consecutive turns (

T

). Dem. = average latency on demand turns (model generates a response); N-D. = average latency on non-demand turns (model outputs [NO_DEMAND] ); Avg. = overall average. Demand turns consistently incur higher latency due to longer generated outputs. Bold = fastest; Italic = second fastest.

Figure 9: Long-term memory case study and user study. Top: Case studies illustrating three types of long-term memory in Pask-MM : (1) background memory for understanding user roles and needs, (2) knowledge memory via

\mathcal{M}_{\text{global}}

for retrieving past facts, and (3) preference memory for personalization. Bottom-left: User ratings (20 participants per scenario) are mostly around 3–4, with learning rated highest, work moderate, and daily lowest with some scores near 1–2, highlighting increasing difficulty from structured to open-ended settings. Bottom-right: Quiz results (5 participants per group) show that Pask improves average scores from about 6 to 7–7.5 after a 5-minute learning task, demonstrating its effectiveness in knowledge acquisition.

PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory

Abstract

Figures & tables

Proactive Agents

ProMemAgent: Long-Horizon Proactive Assistance with Context-Aware Prospective Memory from Sensory Perceptions

$π$ -Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents

Abstract

Proactive Agents

Explore similar work

ProMemAgent: Long-Horizon Proactive Assistance with Context-Aware Prospective Memory from Sensory Perceptions

πππ-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents

$π$ -Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows