AuthorsRunnan Fang, Yuan Liang, Xiaobin Wang et al.
TL;DR
Memp uses Build–Retrieve–Update procedural memories distilled from trajectories to cut ALFWorld test steps from 23.76 to 15.01 while raising success from 42.14% to 77.86%.
Read our summary here, or open the publisher PDF on the next tab.
THE PROBLEM
Memp targets agents whose procedural memory is brittle, manually engineered, or entangled in static parameters, leading to slow, inaccurate multi step execution.
When TravelPlanner and ALFWorld tasks repeat structural patterns, agents still restart from scratch, wasting tokens and failing to reuse skills, tool sequences, and recovery tactics.
HOW IT WORKS
Memp centers on Build, Retrieve, and Update modules that transform trajectories into scripts, trajectories, and combined Proceduralization stored in a procedural memory library.
You can think of Memp like a layered cache: raw trajectories are disk logs, abstract scripts are indexed functions, and retrieval is a semantic card catalog over prior runs.
This design lets Memp inject distilled procedural knowledge into πmp(at|st), enabling continual skill reuse far beyond what a plain context window or static prompt templates can support.
DIAGRAM
This diagram shows how Memp uses trajectories and rewards to build, retrieve, and update procedural memory across sequential tasks.
DIAGRAM
This diagram shows how Memp evaluates different Build, Retrieve, and Update strategies on TravelPlanner and ALFWorld.
PROCESS
Build
In Build, Memp applies the builder B to each task trajectory τ and reward r, creating m_pt and aggregating them into the procedural memory library Mem.
Retrieve
In Retrieve, Memp encodes the new task t_new with ϕ and selects m_retrieved via cosine similarity using Key Query or Key AveFact strategies.
Update
In Update, Memp applies U = Add ⊖ Del ⊕ Update using Vanilla Memory Update, Validation, or Adjustment based on execution feedback E(t).
Proceduralization
In Proceduralization, Memp combines full trajectories with high level scripts, then feeds this hybrid procedural memory into the agent policy πmp(at|st).
KEY CONTRIBUTIONS
Task agnostic procedural memory framework
Memp formalizes procedural memory as Mem = Σ m_pt and integrates Build, Retrieve, and Update modules, turning trajectories into reusable skills across TravelPlanner and ALFWorld.
Systematic Build and Retrieve strategies
Memp compares Script, Trajectory, and Proceduralization storage plus Random Sample, Key Query, and Key AveFact retrieval, showing Proceduralization with AveFact yields the strongest gains.
Online memory update mechanisms
Memp introduces Vanilla Memory Update, Validation, and Adjustment, demonstrating reflexion style Adjustment yields up to +0.7 reward and 14 step reduction over other updates.
RESULTS
ALFWorld Test
77.86%
+35.72 over GPT-4o No Memory (42.14%)
ALFWorld Steps
15.01 steps
-8.75 steps vs GPT-4o No Memory (23.76)
TravelPlanner #CS
79.94
+8.01 over GPT-4o No Memory (71.93)
TravelPlanner Steps
14.62 steps
-3.22 steps vs GPT-4o No Memory (17.84)
On TravelPlanner and ALFWorld, which test long horizon tool use and embodied housework, Memp’s Proceduralization with GPT-4o boosts success and cuts steps relative to the No Memory baseline. These numbers show Memp converts prior trajectories into concrete efficiency and accuracy gains for agents.
BENCHMARK
On TravelPlanner and ALFWorld, which test long horizon tool use and embodied housework, Memp’s Proceduralization with GPT-4o boosts success and cuts steps relative to the No Memory baseline. These numbers show Memp converts prior trajectories into concrete efficiency and accuracy gains for agents.
BENCHMARK
Success rate (%) on ALFWorld Test for GPT-4o with No Memory, Script, Trajectory, and Proceduralization.
KEY INSIGHT
Procedural memory built by GPT-4o and transferred to Qwen2.5-14B raises TravelPlanner completion by 5% while cutting average steps by 1.6.
This is surprising because smaller models usually lag far behind, yet Memp shows a static memory bank from a stronger agent can materially boost weaker agents without retraining.
WHY IT MATTERS
Memp unlocks reusable, updatable procedural memory that grows across tasks, giving agents a concrete way to accumulate skills over time.
Builders can now treat trajectories as a shared procedural memory asset, distill it once with a strong agent, and plug it into weaker or specialized agents to gain efficiency and accuracy immediately.
Nikhil Verma
· 2026
Focus Agent adds start_focus, complete_focus, a persistent Knowledge block, and an optimized Persistent Bash plus String-Replace Editor scaffold to actively compress context during long software-engineering tasks. On five hard SWE-bench Lite instances against a Baseline ReAct agent, Focus Agent achieves 22.7% token reduction (14.9M → 11.5M) while matching 3/5 = 60% task success.
Xingyu Lyu, Jianfeng He et al.
· 2026
ADAM combines Anchor extraction, Distribution estimation, Anchor selection, and Query generation to adaptively probe agent memory via an auxiliary generator and entropy based selection. On the EHRAgent benchmark with Llama2-7b-chat, ADAM reaches EQ=77 and ASR=1.00, compared to MEXTRA’s EQ=44 and ASR=0.89.
Shannan Yan, Jingchen Ni et al.
· 2026
AdaMem organizes dialogue history into Working Memory, Episodic Memory, Persona Memory, and Graph Memory coordinated by a Memory Agent, Research Agent, and Working Agent. On LoCoMo with GPT-4.1-mini, AdaMem achieves 44.65 F1 overall, beating the best baseline LangMem at 41.76 F1 by +2.89.
Answers use this explainer on Memory Papers.
Checking…