LiveAsset: Learning Intent Assets from Corrective Interactions for Agent Runtime Control
Organizations: Fudan University · Lenovo Group Ltd
Abstract
Large language model (LLM) agents acting across web applications and online services often need multi-turn corrections to align their work with users' underspecified goals and preferences. In practice, users may identify problems in the current outcome without specifying the desired result, so learning user intentions requires interpreting each correction against the agent's preceding and revised outcomes. These expectations are often connected to a particular context, making it hard to know when they apply and how to ensure the agent later acts as the user expects. To this end, we propose LiveAsset, an intent harness that learns reusable intent assets from corrective interactions and uses them for runtime control of agent execution. LiveAsset jointly interprets each correction with the agent's original and revised results to infer user intent, incrementally updating the assets while preserving earlier requirements that remain applicable. The learned requirements guide agent execution from task entry and provide criteria for runtime verification, which uses the explanations to assess applicability before each reply is delivered and directs the agent to revise the result to address unmet requirements while preserving those already satisfied. Following a learning phase in which simulated users progressively reveal requirements through multi-turn corrections, we evaluate LiveAsset using same-task replay of the original requests on π-Bench, PERMA, and Vita and cross-task transfer on PAST-Bench and SkillEvolBench. Experiments show that LiveAsset better fulfills requirements learned from corrective interactions and improves performance on these benchmarks compared with memory, skill, and rule-based harness baselines. Code is available at github.com/landian60/LiveAsset.
Figures & tables
| Same-task replay | Transfer to changed tasks | ||||||||||||
| -Bench | PERMA | Vita | PAST-Bench | SkillEvolBench | |||||||||
| Method | Satisfaction | PROC | Satisfaction | TC | Satisfaction | Reward | All | Near | Far | All | T4 | T5 | T6 |
| Actor: GPT-6 Luna | |||||||||||||
| Base agent | 0.218 | 0.466 | 0.132 | 0.114 | 0.228 | 0.015 | 0.641 | 0.648 | 0.634 | 0.815 | 0.809 | 0.840 | 0.794 |
| Raw history | 0.801 | 0.794 | 0.881 | 0.929 | 0.789 | 0.424 | 0.933 | 0.950 | 0.910 | 0.857 | 0.892 | 0.858 | 0.821 |
| Skill | 0.554 | 0.681 | 0.704 | 0.657 | 0.733 | 0.545 | 0.836 | 0.839 | 0.833 | 0.854 | 0.882 | 0.855 | 0.826 |
| Method / variant | DeepSeek V4.1-Flash | GPT-6 Luna | ||
|---|---|---|---|---|
| Sat. | Task score | Sat. | Task score | |
| -Bench (PROC) | ||||
| LiveAsset (Full) | 0.921 | 0.964 | 0.925 | 0.969 |
| w/o explanation | 0.827 | 0.833 | 0.788 | 0.912 |
| w/o context | 0.862 | 0.852 | 0.881 | 0.908 |
| w/o runtime | 0.912 | 0.915 | 0.883 | 0.924 |
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
| Benchmark | ||
|---|---|---|
| -Bench | 2.90 | 0.70 |
| PERMA | 2.11 | 2.09 |
| Vita | 4.27 | 0.85 |
| PAST-Bench | 1.83 | 1.83 |
| SkillEvolBench | 1.53 | 1.53 |
| Benchmark | Learning and evaluation scope | Metric |
|---|---|---|
| -Bench | 100 tasks, 5 personas | Exposed checklist satisfaction; PROC with delivery evidence. |
| PERMA | 10 users, 580 user–query pairs; 1,094 checkpoints (705 single-domain, 389 multi-domain) | Exposed preference satisfaction; task completion (TC). |
| Vita | 56 users, 771 personalized subtasks | Exposed rubric satisfaction; native trajectory reward. |
| PAST-Bench | 26 families, 204 episodes; 34 near- and 26 far-transfer evaluation targets | Adapted task-outcome score, excluding prescribed memory/skill channels. |
| SkillEvolBench | 6 environments, 30 families, 180 tasks; T1–T3 learning and T4–T6 testing, 90 each | Native verifier reward and process/outcome checks. |
| DeepSeek V4.1-Flash | GPT-6 Luna | |||
|---|---|---|---|---|
| Method | Test-time (k/run) | Build (k/task) | Test-time (k/run) | Build (k/task) |
| LiveAsset | 367.1 | 72.7 | 205.9 | 66.3 |
| Base agent | 243.6 | – | 154.2 | – |
| Raw history | 276.9 | – | 293.0 | – |
| Skill | 410.9 | 380.8 | 170.6 | 259.7 |
| Mem0 | 308.0 | 99.4 | 155.6 | 107.0 |
LLM Agent Harnesses
LLM agent harnesses are the software and runtime systems that organize an agent’s tools, context, state, execution, and safeguards.
See all 428 papers