Evolve¶
Self-improving agents through iterations.
Evolve helps AI agents learn from experience. It turns past trajectories into reusable guidelines that help agents complete future tasks, without changing model weights.
The Lite version is designed to effortlessly slot into existing agent assistants like Claude Code and Codex. The full service uses a combination of an MCP server for tool integration, vector storage for memory, and LLM-based conflict resolution to refine its knowledge base. It also supports guideline consolidation, clustering related guidelines and merging equivalent advice while preserving support counts and source provenance.
On AppWorld's held-out test split, a GPT-4.1 ReAct agent with Evolve increased scenario completion from 50.0% to 64.3% (+14.3 percentage points).
The Announcement → Check out the Blog → Read the Paper → See the Results →
Research highlights¶
| Finding | Reported result |
|---|---|
| More repeatable success | AppWorld tasks passing all five attempts increased from 53% to 66%, using sibling-task guidelines with GPT-4.1. |
| Efficient learning | With gpt-oss-120b, AppWorld task completion increased from 39.9% to 56.0% using curated retrieval. |
| Lifts frontier and non-frontier models | On τ²-bench, Evolve lifts both frontier and non-frontier models (held-out Pass^4: GPT-5.5 55% → 70%; GPT-4.1 57.5% → 67.5%). |
These are separate benchmark experiments with different metrics, models, and memory configurations. Follow each link for its evaluation protocol and sources.
Latest from Evolve¶
Research, releases, and practical findings from the Evolve team.
- 2026-10-20 · Article — ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model Learned guidelines raise GPT-4.1's held-out retail Pass^4 from 57.5% to 67.5%; the article also compares pending custom submissions with an October 12 leaderboard snapshot.
- 2026-09-25 · Paper — Memory as Middleware for Self-Improving AI Agents The case for agent memory as a pluggable middleware layer, with Evolve as the reference implementation (to appear at Middleware 2026).
- 2026-09-15 · Article — Your Agent Aced the Task. Will It Do It Again? Diagnosing where an agent's decisions wobble and stabilizing them so success repeats.
- 2026-09-08 · Paper — Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course Turning unstable trajectory steps into episodic memory to keep agents consistent across repeated runs.
- 2026-08-18 · Article — How Much Memory Does Your Agent Actually Need? Why agent memory should be calibrated to the model instead of simply increased.
- 2026-08-11 · Article — Thinking of ACE? We Can Do It with Fewer Tokens Comparing Evolve's targeted guideline retrieval with ACE's playbook approach and token usage.
- 2026-04-08 · Article — ALTK‑Evolve: On‑the‑Job Learning for AI Agents An introduction to learning reusable guidance from agent trajectories.
- 2026-04-07 · Announcement — IBM introduces ALTK Evolve Evolve is opened to builders creating agents that learn from experience.
- 2026-03-11 · Paper — Trajectory-Informed Memory Generation for Self-Improving Agent Systems The research framework and evaluation underlying Evolve.
When setting up API keys and extra services are too much
Total Control
Under Development
-
MCP Server
Exposes tools to get guidelines and save trajectories.
-
Conflict Resolution
Intelligently merges new insights with existing guidelines using LLMs.
-
Trajectory Analysis
Automatically analyzes agent trajectories to generate guidelines and best practices.
-
Milvus Integration
Uses Milvus (or Milvus Lite) for efficient vector storage and retrieval.
Guides¶
- Configuration: Configure models, backends, and environment variables.
- Low-Code Tracing: Instrument agents with Phoenix and verify end-to-end tracing.
- Phoenix Sync: Pull trajectories from Phoenix and generate stored guidelines.
- Extract Trajectories: Export Phoenix traces into an OpenAI-style message format.
Reference¶
- CLI Reference: Manage namespaces, entities, and sync jobs from the command line.
- Policies: Structured policy entities and how to retrieve them with MCP tools.
Demos¶
The video shows an earlier release
This April 2026 video uses an Evolve Lite mode and explicit learn/recall skills. Current Bob releases use always-on rules. Follow the current tutorial for installation and usage.
How It Works¶
Evolve analyzes agent trajectories to extract guidelines and best practices, then recalls them in future sessions. It supports both a lightweight file-based mode (Evolve Lite) and a full mode backed by an MCP server with vector storage, LLM-based conflict resolution, and guideline consolidation.