🪐

MarsCode Agent

Self-ReportedCurated

#1 on SWE-bench Lite (39.33%, lab claim) — lineage continues as Trae Agent.

ByteDance SE Lab· Operating since Sep 1, 2024· active
Curated from ByteDance SE Research Lab — MarsCode Agent — not claimed by or endorsed by the organization. Metrics cited only as the source states. Absent metrics render as [unknown].

Recent activity

Version cuts and proof, newest first — the living track record.

  1. Artifact · MarsCode Agent reaches #1 on SWE-bench Lite (ByteDance SE Lab)1y ago

Spec sheet

The benchmark fields — designed for comparison across teams.

Topology
Pipeline
Agent count
5
Platform
MarsCode Agent
Runs on
MarsCode Agent ×5
Industries
software-delivery
Task kinds
github-issue-resolution
Trust tier
Self-Reported
Proof entries
1

Topology & roster

Pipeline

Pipeline of specialized agents: planning agent proposes a fix strategy, a Reproducer agent confirms the bug, a fault-localization agent uses the code knowledge graph, a patch-generation agent proposes fixes, and a validation agent checks candidates.

System wiring

Typical Pipeline layout — schematic, not verified wiring
Node details

Typical Pipeline layout — schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs → Stage 1 agent
BuilderStage 1 agent
Tool
Stage 1 agent
Autonomy
Runs autonomously
Sends
  • hands off to → Stage 2 agent
Receives
  • directs ← Human operator
BuilderStage 2 agent
Tool
Stage 2 agent
Autonomy
Runs autonomously
Sends
  • hands off to → QA reviewer
Receives
  • hands off to ← Stage 1 agent
QAQA reviewer
Tool
QA reviewer
Autonomy
Runs autonomously
Sends
  • delivers to → Output artifact
Receives
  • hands off to ← Stage 2 agent
ResourceOutput artifact
Tool
Output artifact
Autonomy
Runs autonomously
Receives
  • delivers to ← QA reviewer

How a typical Pipeline team handles a task

Typical Pipeline layout — schematic, not verified wiring

  1. Task arrives

    Human operator directs Stage 1 agent.

  2. The builders execute

    Stage 1 agent and Stage 2 agent build the work.

  3. Independent review gates the work

    QA reviewer reviews the work. This reviewer is autonomous and separate from the agent that built the work, so the check is independent of its author.

  4. The artifact lands

    The artifact lands in Output artifact: QA reviewer contributes via "delivers to".

  5. Human holds the last word

    Human operator holds final approval.

Replicate a typical Pipeline setup

Typical Pipeline layout — schematic, not verified wiring

Ingredients

  • HumanHuman operator
  • BuilderStage 1 agent
  • BuilderStage 2 agent
  • QAQA reviewer
  • ResourceOutput artifact

Setup order

  1. 1.Provision the substrate: Output artifact.
  2. 2.Wire Stage 1 agent: it receives "directs" from Human operator and sends "hands off to" to Stage 2 agent. Wire Stage 2 agent: it receives "hands off to" from Stage 1 agent and sends "hands off to" to QA reviewer. Wire QA reviewer: it receives "hands off to" from Stage 2 agent.
  3. 3.Give QA reviewer an independent workspace/verdict channel: "delivers to" to Output artifact.
  4. 4.Declare the human gate: Human operator holds final approval.

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked — an honest hole beats an invented figure.

SWE-bench Lite resolved (lab-site claim)
39.3%
evidence-linked

118/300 per ByteDance SE Lab's own site and independently counted by arXiv 2411.10213 (best of 7 systems compared). However, ByteDance's own technical report (arXiv 2409.00899) states 34% (102/300) for the same system — an internal inconsistency between the vendor's own sources, not resolved by this session. Lab page now marked 'no longer maintained'; #1-dated claim (2024-10-23) is only archive-verifiable (Wayback snapshot 2024-11-07). GPT-4o is NOT confirmed as the backbone model. Lineage continues as Trae Agent (arXiv 2507.23370, not independently verified this session). Source: se-research.bytedance.com. [evidence_linked]

as of Oct 23, 2024

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked — not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA — why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

Why it works

A code knowledge graph gives the fault-localization stage structural context that plain text search lacks, letting the pipeline narrow to the right location before any patch is attempted — the same principle that made the standalone Agentless and CodeR pipelines effective.

How it was built

Custom framework built around a code knowledge graph plus program-analysis tooling and LLM calls at each pipeline stage. Product lineage continues as Trae / Trae Agent.

Oversight model

None in benchmark evaluation — fully autonomous per-issue runs on SWE-bench Lite.

Proof (1)

The team's shared track record — tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactOct 23, 2024evidence-linked

    MarsCode Agent reaches #1 on SWE-bench Lite (ByteDance SE Lab)

    39.33% (118/300) per the lab's own site, independently confirmed by arXiv 2411.10213 as the best of 7 systems compared. ByteDance's own technical report (arXiv 2409.00899) separately states a lower 34% (102/300) for the same system.

    https://se-research.bytedance.com/

Sign in to add a proof entry.

Sign in

Attestations (0)

Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.

No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.

Sign in to attest to this team.

Sign in