Problem
Research questions and friction points this paper is trying to address.
procedural memory
autonomous agents
long-horizon tasks
procedural failures
state tracking
CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories
🤖 AI Summary
为解决自主计算机使用代理的程序性失败问题，提出CONTRAMEM框架，通过对比多模型轨迹学习自进化程序记忆，提高任务成功率。
📝 Abstract
Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and verifier-sensitive writes, yet they remain prone to procedural failures: misreading application state, tool semantics, or task progress. Procedural memory promises more consistent decisions and less redundant exploration, but constructing high-quality memory without model training remains challenging. We introduce CONTRAMEM, a source-flexible, training-free framework for self-evolving procedural memory that treats same-task outcome variation as supervision: differences in correctness, efficiency, recovery, and failure modes expose outcome-relevant procedural distinctions, distilled into a compact bank of app-level Function Cards and task-level Skill Cards that evolves through localized curation rather than append-only accumulation or whole-bank rewriting. On held-out GAIA2/ARE computer-use tasks, CONTRAMEM more than doubles the success rate across the three source-model targets (26.2% to 55.3%), with consistent per-model gains (GPT-5.5: 27.5 to 61.0; Claude Sonnet 4.6: 28.0 to 52.5; DeepSeek V4 Pro: 23.0 to 52.5). The same bank transfers unchanged to the unseen Qwen3.7 Plus (18.5 to 35.5), indicating transferable procedural knowledge rather than model-specific behavior. The same construction carries over unchanged to AppWorld, beating both no memory and its own single-source self-memory variant for all three mid-tier agents on both public test splits. Under a matched trajectory budget, heterogeneous multi-model trajectories yield stronger memory than self- or same-model multi-rollout memory: the margin comes from contrastive behavioral diversity, not stronger source agents or more sampling.
Innovation
Methods, ideas, or system contributions that make the work stand out.
self-evolving procedural memory
contrastive multi-model trajectories
function cards
skill cards
local curation
🔎 Similar Papers
No similar papers found.
