diff --git a/evolution/core/config.py b/evolution/core/config.py
index 39b1090..81d2d51 100644
--- a/evolution/core/config.py
+++ b/evolution/core/config.py
@@ -37,6 +37,14 @@ class EvolutionConfig:
     # for the actionable hint surfaced to users.
     reflection_minibatch_size: int = 3
 
+    # GEPA acceptance criterion. "improvement_or_equal" (default) accepts
+    # plateau-equal candidates so noisy LM-judge ties don't reject "true
+    # zero-difference" mutations ~50% of the time; "strict_improvement"
+    # preserves the gepa<0.1.2 implicit behavior. Forwarded as the literal
+    # kwarg expected by gepa.optimize via dspy.GEPA's gepa_kwargs passthrough
+    # (valid gepa values: "strict_improvement", "improvement_or_equal").
+    gepa_acceptance: str = "improvement_or_equal"
+
     # Per-role model overrides. When set, treated as explicit LiteLLM model
     # strings that bypass Hermes resolution. When None, get_lm() falls back
     # to resolve_default_lm() against ~/.hermes/config.yaml + auth.json +
diff --git a/evolution/core/run_inputs.py b/evolution/core/run_inputs.py
index 7862b1c..213dac6 100644
--- a/evolution/core/run_inputs.py
+++ b/evolution/core/run_inputs.py
@@ -19,6 +19,7 @@ def build_run_inputs(
     optimizer_model: str,
     quality_gate_preset: str,
     eval_source: str,
+    gepa_acceptance: str,
     fitness_profile: Optional[str] = None,
     enable_confusable_bucket: Optional[bool] = None,
 ) -> dict[str, Any]:
@@ -37,6 +38,7 @@ def build_run_inputs(
         "holdout_ratio": config.holdout_ratio,
         "quality_gate_preset": quality_gate_preset,
         "eval_source": eval_source,
+        "gepa_acceptance": gepa_acceptance,
     }
     if fitness_profile is not None:
         run_inputs["fitness_profile"] = fitness_profile
diff --git a/evolution/skills/evolve_skill.py b/evolution/skills/evolve_skill.py
index 71c78f7..cc69348 100644
--- a/evolution/skills/evolve_skill.py
+++ b/evolution/skills/evolve_skill.py
@@ -298,6 +298,7 @@ def _default_gepa_runner(
     instruction_proposer=None,
     reflection_model: Optional[str] = None,
     reflection_minibatch_size: int = 3,
+    gepa_acceptance: str = "improvement_or_equal",
 ):
     # max_tokens=32000 satisfies DSPy's reasoning-model floor of 16000
     # (DSPy raises ValueError below that).
@@ -327,6 +328,7 @@ def _default_gepa_runner(
         track_stats=True,
         instruction_proposer=instruction_proposer,
         reflection_minibatch_size=reflection_minibatch_size,
+        gepa_kwargs={"acceptance_criterion": gepa_acceptance},
     )
     return optimizer.compile(baseline_module, trainset=trainset, valset=valset)
 
@@ -385,6 +387,7 @@ def _build_optimizer_and_compile(
     instruction_proposer=None,
     reflection_model: Optional[str] = None,
     reflection_minibatch_size: int = 3,
+    gepa_acceptance: str = "improvement_or_equal",
     _gepa_runner=_default_gepa_runner,
     _mipro_runner=_default_mipro_runner,
 ):
@@ -407,6 +410,7 @@ def _build_optimizer_and_compile(
             instruction_proposer=instruction_proposer,
             reflection_model=reflection_model,
             reflection_minibatch_size=reflection_minibatch_size,
+            gepa_acceptance=gepa_acceptance,
         )
         return optimized, "GEPA"
     except CostCeilingExceeded:
@@ -638,6 +642,7 @@ def evolve(
     skip_saturation_check: bool = False,
     force_saturation_check: bool = False,
     gepa_minibatch_size: int = 3,
+    gepa_acceptance: str = "improvement-or-equal",
     closed_loop_suite_path: Optional[Path] = None,
     closed_loop_saturation_threshold: float = 0.95,
     closed_loop_min_iters: int = 3,
@@ -689,6 +694,7 @@ def evolve(
     if holdout_ratio is not None:
         config_kwargs["holdout_ratio"] = holdout_ratio
     config_kwargs["reflection_minibatch_size"] = gepa_minibatch_size
+    config_kwargs["gepa_acceptance"] = gepa_acceptance.replace("-", "_")
     config = EvolutionConfig(**config_kwargs)
     explicit_dirs = [Path(d) for d in (skill_source_dirs or [])]
     if explicit_dirs:
@@ -1010,6 +1016,7 @@ def evolve(
                 instruction_proposer=proposer,
                 reflection_model=config.reflection_model,
                 reflection_minibatch_size=config.reflection_minibatch_size,
+                gepa_acceptance=config.gepa_acceptance,
             )
 
             elapsed = time.time() - start_time
@@ -1101,6 +1108,7 @@ def evolve(
                         optimizer_model=optimizer_model,
                         quality_gate_preset=quality_gate,
                         eval_source=eval_source,
+                        gepa_acceptance=config.gepa_acceptance,
                     ),
                 })
                 console.print(f"  Saved failed variant to {failed_path}")
@@ -1141,6 +1149,7 @@ def evolve(
                 optimizer_model=optimizer_model,
                 quality_gate_preset=quality_gate,
                 eval_source=eval_source,
+                gepa_acceptance=config.gepa_acceptance,
             )
 
             use_cl_primary = (
@@ -1531,6 +1540,7 @@ def evolve(
                     optimizer_model=optimizer_model,
                     quality_gate_preset=quality_gate,
                     eval_source=eval_source,
+                    gepa_acceptance=config.gepa_acceptance,
                 ),
                 schema_version="5",
             )
@@ -1826,6 +1836,18 @@ def evolve(
          "to preserve the proposal count. Aborts at startup if the "
          "value exceeds the trainset size.",
 )
+@click.option(
+    "--gepa-acceptance",
+    "gepa_acceptance",
+    default="improvement-or-equal",
+    type=click.Choice(["strict-improvement", "improvement-or-equal"]),
+    help="GEPA acceptance criterion. 'strict-improvement': only accept "
+         "candidates with strictly better minibatch score (legacy gepa<0.1.2 "
+         "default). 'improvement-or-equal' (default): allow plateau-equal "
+         "candidates for more lateral exploration — the literature-recommended "
+         "fix for noisy LM-judge fitness where strict acceptance rejects "
+         "~50% of true-equal mutations.",
+)
 @click.option(
     "--closed-loop-during-evolution",
     "closed_loop_suite_path",
@@ -1920,6 +1942,7 @@ def main(skill, iterations, eval_source, dataset_path, optimizer_model, reflecti
          skip_saturation_check,
          force_saturation_check,
          gepa_minibatch_size,
+         gepa_acceptance,
          closed_loop_suite_path,
          closed_loop_saturation_threshold,
          closed_loop_min_iters,
@@ -1968,6 +1991,7 @@ def main(skill, iterations, eval_source, dataset_path, optimizer_model, reflecti
             skip_saturation_check=skip_saturation_check,
             force_saturation_check=force_saturation_check,
             gepa_minibatch_size=gepa_minibatch_size,
+            gepa_acceptance=gepa_acceptance,
             closed_loop_suite_path=closed_loop_suite_path,
             closed_loop_saturation_threshold=closed_loop_saturation_threshold,
             closed_loop_min_iters=closed_loop_min_iters,
diff --git a/evolution/tools/evolve_tool.py b/evolution/tools/evolve_tool.py
index 7b62edc..b76388d 100644
--- a/evolution/tools/evolve_tool.py
+++ b/evolution/tools/evolve_tool.py
@@ -383,6 +383,7 @@ def evolve(
     skip_saturation_check: bool = False,
     force_saturation_check: bool = False,
     gepa_minibatch_size: int = 3,
+    gepa_acceptance: str = "improvement-or-equal",
 ) -> dict[str, Any]:
     """Evolve one tool description inside a manifest.
 
@@ -429,6 +430,7 @@ def evolve(
         holdout_ratio=holdout_ratio,
         enable_confusable_bucket=enable_confusable_bucket,
         reflection_minibatch_size=gepa_minibatch_size,
+        gepa_acceptance=gepa_acceptance.replace("-", "_"),
     )
 
     console.print(
@@ -745,6 +747,7 @@ def evolve(
                 track_stats=True,
                 instruction_proposer=proposer,
                 reflection_minibatch_size=config.reflection_minibatch_size,
+                gepa_kwargs={"acceptance_criterion": config.gepa_acceptance},
             )
             optimized_module = optimizer.compile(
                 baseline_module, trainset=trainset, valset=valset,
@@ -800,6 +803,7 @@ def evolve(
                 optimizer_model=optimizer_model,
                 quality_gate_preset=quality_gate,
                 eval_source=eval_source,
+                gepa_acceptance=config.gepa_acceptance,
                 fitness_profile=fitness_profile,
                 enable_confusable_bucket=config.enable_confusable_bucket,
             )
@@ -1239,6 +1243,7 @@ def evolve(
                 optimizer_model=optimizer_model,
                 quality_gate_preset=quality_gate,
                 eval_source=eval_source,
+                gepa_acceptance=config.gepa_acceptance,
                 fitness_profile=fitness_profile,
                 enable_confusable_bucket=config.enable_confusable_bucket,
             )
@@ -1476,6 +1481,18 @@ def evolve(
          "~10 to preserve the proposal count. Aborts at startup if the "
          "value exceeds the trainset size.",
 )
+@click.option(
+    "--gepa-acceptance",
+    "gepa_acceptance",
+    default="improvement-or-equal",
+    type=click.Choice(["strict-improvement", "improvement-or-equal"]),
+    help="GEPA acceptance criterion. 'strict-improvement': only accept "
+         "candidates with strictly better minibatch score (legacy gepa<0.1.2 "
+         "default). 'improvement-or-equal' (default): allow plateau-equal "
+         "candidates for more lateral exploration — the literature-recommended "
+         "fix for noisy LM-judge fitness where strict acceptance rejects "
+         "~50% of true-equal mutations.",
+)
 @click.option(
     "--closed-loop-in-valset/--no-closed-loop-in-valset",
     "closed_loop_in_valset",
@@ -1530,6 +1547,7 @@ def main(
     skip_saturation_check: bool,
     force_saturation_check: bool,
     gepa_minibatch_size: int,
+    gepa_acceptance: str,
     closed_loop_suite_path: Optional[Path],
     closed_loop_hermes_repo: Optional[Path],
     closed_loop_saturation_threshold: float,
@@ -1583,6 +1601,7 @@ def main(
             skip_saturation_check=skip_saturation_check,
             force_saturation_check=force_saturation_check,
             gepa_minibatch_size=gepa_minibatch_size,
+            gepa_acceptance=gepa_acceptance,
         )
     except HermesProviderError as exc:
         # Render a clean error panel instead of dumping a Python traceback —
diff --git a/pyproject.toml b/pyproject.toml
index eed93ce..f5540a9 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -16,6 +16,9 @@ keywords = ["llm", "optimization", "evolution", "dspy", "gepa", "agent", "skill"
 
 dependencies = [
     "dspy>=3.2.0,<3.3",
+    # Pinned to PR-304 merge SHA for the acceptance_criterion API; swap to
+    # a PyPI version when 0.1.2 ships (latest released 0.1.1 predates the merge).
+    "gepa @ git+https://github.com/gepa-ai/gepa.git@5e24ee5c8e1857a62a1ba19731de9da45ffb6f1b",
     # Pinned because lm_timing_callback.py uses litellm.failure_callback
     # (a module-level list mutation API) and dspy.LM forwards
     # request_timeout/num_retries to litellm. Both are stable at 1.82
@@ -47,6 +50,13 @@ dev = [
 Homepage = "https://github.com/jramos/agent-self-evolution"
 Repository = "https://github.com/jramos/agent-self-evolution"
 
+[tool.uv]
+# DSPy 3.2.0 hard-pins gepa[dspy]==0.0.27; override to take PR-304's
+# acceptance_criterion API before 0.1.2 ships on PyPI.
+override-dependencies = [
+    "gepa @ git+https://github.com/gepa-ai/gepa.git@5e24ee5c8e1857a62a1ba19731de9da45ffb6f1b",
+]
+
 [tool.setuptools.packages.find]
 include = ["evolution*"]
 
diff --git a/reports/calibration_findings.md b/reports/calibration_findings.md
index cf7ec97..be036ad 100644
--- a/reports/calibration_findings.md
+++ b/reports/calibration_findings.md
@@ -87,3 +87,25 @@ The `--max-absolute-chars 12000` override applied to Stage 7 validation runs (so
 ## Audit trail
 
 Full campaign artifacts — runbook, analysis scripts, `study_*_results.json`, and per-run `output/<skill>/<ts>/{gate_decision,band_holdout,metrics}.json` — live on the `archive/2026-deploy-gate-calibration` branch. No-op merge to main; the report and the one-line preset change are the only durable changes from this campaign.
+
+## Path D — GEPA acceptance criterion (improvement-or-equal default)
+
+The framework now defaults `acceptance_criterion` to `improvement_or_equal`
+for the underlying `gepa.optimize` call, replacing the implicit strict
+behavior baked into gepa <0.1.2. Flag: `--gepa-acceptance
+{strict-improvement,improvement-or-equal}` on `evolve_skill` and `evolve_tool`.
+
+Why: strict-elitist acceptance under noisy LM-judge fitness rejects
+"true zero-difference" candidates roughly half the time, narrowing
+search and reducing Pareto-frontier diversity for no benefit. GEPA's
+Algorithm 1 only says "if σ′ improved" — the strict tiebreak was an
+implementation artifact, not a paper claim. Literature on this is
+unambiguous (Beyer 2000 on noisy elitism; Aizawa & Wah 1994 and
+Rakshit et al. 2017 on threshold/relaxed acceptance for noisy fitness).
+
+Upstream: gepa-ai/gepa PR #304 (merged 2026-04-06) introduced the
+configurable `acceptance_criterion` API with `"strict"` and
+`"improvement_or_equal"` shortcuts. We pin gepa to the merge SHA via a
+git dependency until 0.1.2 ships on PyPI (0.1.1 was uploaded
+2026-03-16, three weeks before the merge); migration path is a one-line
+swap to `"gepa>=0.1.2"` once it's published.
diff --git a/tests/core/test_run_inputs.py b/tests/core/test_run_inputs.py
index e525d55..2857575 100644
--- a/tests/core/test_run_inputs.py
+++ b/tests/core/test_run_inputs.py
@@ -27,6 +27,7 @@ def test_skill_side_shape(self):
             optimizer_model="openai/gpt-4.1",
             quality_gate_preset="default",
             eval_source="synthetic",
+            gepa_acceptance="improvement_or_equal",
         )
         assert set(result.keys()) == {
             "seed",
@@ -39,7 +40,9 @@ def test_skill_side_shape(self):
             "holdout_ratio",
             "quality_gate_preset",
             "eval_source",
+            "gepa_acceptance",
         }
+        assert result["gepa_acceptance"] == "improvement_or_equal"
 
     def test_tool_side_adds_fitness_profile_and_confusable_bucket(self):
         config = _fake_config()
@@ -50,6 +53,7 @@ def test_tool_side_adds_fitness_profile_and_confusable_bucket(self):
             optimizer_model="openai/gpt-4.1",
             quality_gate_preset="default",
             eval_source="synthetic",
+            gepa_acceptance="strict_improvement",
             fitness_profile="balanced",
             enable_confusable_bucket=True,
         )
@@ -64,9 +68,11 @@ def test_tool_side_adds_fitness_profile_and_confusable_bucket(self):
             "holdout_ratio",
             "quality_gate_preset",
             "eval_source",
+            "gepa_acceptance",
             "fitness_profile",
             "enable_confusable_bucket",
         }
+        assert result["gepa_acceptance"] == "strict_improvement"
         assert result["fitness_profile"] == "balanced"
         assert result["enable_confusable_bucket"] is True
 
@@ -78,6 +84,7 @@ def test_resolved_lms_matches_helper_output(self):
             optimizer_model="openai/gpt-4.1",
             quality_gate_preset="default",
             eval_source="synthetic",
+            gepa_acceptance="improvement_or_equal",
         )
         expected = resolved_lms_dump(
             optimizer="openai/gpt-4.1",
@@ -98,6 +105,7 @@ def test_enable_confusable_bucket_round_trips_when_passed(self):
             optimizer_model="openai/gpt-4.1",
             quality_gate_preset="default",
             eval_source="synthetic",
+            gepa_acceptance="improvement_or_equal",
             fitness_profile="balanced",
             enable_confusable_bucket=config.enable_confusable_bucket,
         )
diff --git a/tests/skills/test_evolve_skill_validation_flow.py b/tests/skills/test_evolve_skill_validation_flow.py
index 656c970..8a49759 100644
--- a/tests/skills/test_evolve_skill_validation_flow.py
+++ b/tests/skills/test_evolve_skill_validation_flow.py
@@ -878,3 +878,90 @@ def _raise_after_handler_attach(self, *args, **kwargs):
             f"evolve_skill.evolve() leaked {after - before} root-logger "
             f"handler(s) across two calls"
         )
+
+
+def _fake_skill_dataset(n: int = 50):
+    """Real-shaped EvalDataset with n fake examples — no LM calls."""
+    examples = [
+        EvalExample(task_input=f"task {i}", expected_behavior=f"rubric {i}")
+        for i in range(n)
+    ]
+    return EvalDataset(
+        train=examples[:30], val=examples[30:40], holdout=examples[40:50],
+    )
+
+
+class TestGepaAcceptanceFlag:
+    """--gepa-acceptance threads through to dspy.GEPA's gepa_kwargs,
+    forwarded onward to gepa.optimize as acceptance_criterion."""
+
+    @pytest.fixture
+    def skill_dir(self, tmp_path):
+        skills_root = tmp_path / "skills"
+        skill_path = skills_root / "demo-skill"
+        skill_path.mkdir(parents=True)
+        (skill_path / "SKILL.md").write_text(
+            "---\nname: demo-skill\ndescription: a test skill\n---\n\nDo X.\n"
+        )
+        return skills_root
+
+    def _run_with_capture(self, skill_dir: Path, extra_cli_args: list[str]):
+        captured: dict = {}
+        import dspy
+        original_init = dspy.GEPA.__init__
+
+        def recording_init(self, *args, **kwargs):
+            original_init(self, *args, **kwargs)
+            captured["gepa_kwargs"] = dict(self.gepa_kwargs)
+
+        fake_candidate = MagicMock()
+        fake_candidate.skill_text = "evolved skill text"
+        fake_module = MagicMock()
+        fake_module.skill_text = "evolved skill text"
+        fake_module.detailed_results = SimpleNamespace(
+            candidates=[fake_candidate],
+            val_aggregate_scores=[1.0],
+            best_idx=0,
+        )
+        fake_builder = MagicMock()
+        fake_builder.generate.return_value = _fake_skill_dataset()
+        with patch(
+            "evolution.skills.evolve_skill.SyntheticDatasetBuilder", return_value=fake_builder
+        ), patch(
+            "evolution.skills.evolve_skill._preflight_lm_credentials"
+        ), patch("evolution.skills.evolve_skill.dspy.GEPA.__init__", recording_init), patch(
+            "evolution.skills.evolve_skill.dspy.GEPA.compile", return_value=fake_module
+        ), patch(
+            "evolution.skills.evolve_skill._holdout_evaluate_with_metric",
+            return_value=(0.6, [0.6] * 10),
+        ):
+            runner = CliRunner()
+            result = runner.invoke(
+                evolve_skill_cli,
+                ["--skill", "demo-skill", "--skill-source-dir", str(skill_dir),
+                 "--iterations", "1", "--no-preflight",
+                 "--no-saturation-check", *extra_cli_args],
+            )
+        return captured, result
+
+    def test_gepa_acceptance_default_passes_improvement_or_equal(self, skill_dir):
+        captured, result = self._run_with_capture(skill_dir, extra_cli_args=[])
+        assert "gepa_kwargs" in captured, (
+            f"dspy.GEPA was never constructed; CLI output: {result.output}"
+        )
+        assert captured["gepa_kwargs"].get("acceptance_criterion") == "improvement_or_equal", (
+            f"Expected default acceptance_criterion=improvement_or_equal; "
+            f"got {captured['gepa_kwargs']!r}. CLI output: {result.output}"
+        )
+
+    def test_gepa_acceptance_strict_passes_strict_improvement(self, skill_dir):
+        captured, result = self._run_with_capture(
+            skill_dir, extra_cli_args=["--gepa-acceptance", "strict-improvement"],
+        )
+        assert "gepa_kwargs" in captured, (
+            f"dspy.GEPA was never constructed; CLI output: {result.output}"
+        )
+        assert captured["gepa_kwargs"].get("acceptance_criterion") == "strict_improvement", (
+            f"Expected acceptance_criterion=strict_improvement; "
+            f"got {captured['gepa_kwargs']!r}. CLI output: {result.output}"
+        )
diff --git a/tests/tools/test_evolve_tool_validation_flow.py b/tests/tools/test_evolve_tool_validation_flow.py
index ca8f889..05198f2 100644
--- a/tests/tools/test_evolve_tool_validation_flow.py
+++ b/tests/tools/test_evolve_tool_validation_flow.py
@@ -913,3 +913,78 @@ def _force_reject(self, artifact_text, baseline_text, bootstrap_result):
         assert payload["reason"] == "growth_quality_gate"
         assert "benchmark" not in payload
         assert ran["called"] is False
+
+
+class TestGepaAcceptanceFlag:
+    """--gepa-acceptance threads through to dspy.GEPA's gepa_kwargs,
+    forwarded onward to gepa.optimize as acceptance_criterion."""
+
+    def _make_capturing_fake_gepa(self, evolved_module: ToolModule, captured: dict):
+        class _FakeGEPA:
+            def __init__(self, **kwargs):
+                captured["gepa_kwargs"] = dict(kwargs.get("gepa_kwargs") or {})
+                self.kwargs = kwargs
+
+            def compile(self, baseline_module, *, trainset, valset):
+                evolved_module.detailed_results = SimpleNamespace(
+                    candidates=[evolved_module],
+                    val_aggregate_scores=[1.0],
+                    best_idx=0,
+                )
+                return evolved_module
+
+        return _FakeGEPA
+
+    def _run(self, temp_manifest: Path, tmp_path: Path, **evolve_kwargs):
+        manifest = ToolManifest.from_json_file(temp_manifest)
+        run_dir = tmp_path / "run"
+        captured: dict = {}
+        evolved = _build_evolved_module(manifest, EVOLVED_DESCRIPTION)
+        with (
+            patch.object(
+                SyntheticDatasetBuilder,
+                "_call_lm_for_bucket",
+                side_effect=_bucket_side_effect(15, 9, 6),
+            ),
+            patch(
+                "evolution.tools.evolve_tool.dspy.GEPA",
+                new=self._make_capturing_fake_gepa(evolved, captured),
+            ),
+            patch.object(
+                ToolJudge, "score",
+                new=_scripted_judge_score(target_score=0.95, regression_score=0.0),
+            ),
+            patch.object(
+                ToolModule, "forward",
+                new=_scripted_module_forward(expected_tool_for_evolved="search_files"),
+            ),
+        ):
+            evolve(
+                tool_name="search_files",
+                manifest_path=temp_manifest,
+                iterations=1,
+                eval_dataset_size=30,
+                holdout_ratio=0.5,
+                quality_gate="non-inferiority",
+                enable_confusable_bucket=True,
+                output_dir=run_dir,
+                **evolve_kwargs,
+            )
+        return captured
+
+    def test_gepa_acceptance_default_passes_improvement_or_equal(
+        self, temp_manifest: Path, tmp_path: Path
+    ):
+        captured = self._run(temp_manifest, tmp_path)
+        assert captured.get("gepa_kwargs", {}).get("acceptance_criterion") == "improvement_or_equal", (
+            f"Expected default acceptance_criterion=improvement_or_equal; "
+            f"got {captured!r}"
+        )
+
+    def test_gepa_acceptance_strict_passes_strict(
+        self, temp_manifest: Path, tmp_path: Path
+    ):
+        captured = self._run(temp_manifest, tmp_path, gepa_acceptance="strict")
+        assert captured.get("gepa_kwargs", {}).get("acceptance_criterion") == "strict", (
+            f"Expected acceptance_criterion=strict; got {captured!r}"
+        )
diff --git a/uv.lock b/uv.lock
index af728ec..7d7dd48 100644
--- a/uv.lock
+++ b/uv.lock
@@ -6,6 +6,9 @@ resolution-markers = [
     "python_full_version < '3.11'",
 ]
 
+[manifest]
+overrides = [{ name = "gepa", git = "https://github.com/gepa-ai/gepa.git?rev=5e24ee5c8e1857a62a1ba19731de9da45ffb6f1b" }]
+
 [[package]]
 name = "agent-self-evolution"
 version = "0.1.0"
@@ -13,6 +16,7 @@ source = { editable = "." }
 dependencies = [
     { name = "click" },
     { name = "dspy" },
+    { name = "gepa" },
     { name = "litellm" },
     { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
     { name = "numpy", version = "2.4.4", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
@@ -38,6 +42,7 @@ requires-dist = [
     { name = "click", specifier = ">=8.0" },
     { name = "dspy", specifier = ">=3.2.0,<3.3" },
     { name = "dspy", extras = ["optuna"], marker = "extra == 'miprov2'", specifier = ">=3.2.0,<3.3" },
+    { name = "gepa", git = "https://github.com/gepa-ai/gepa.git?rev=5e24ee5c8e1857a62a1ba19731de9da45ffb6f1b" },
     { name = "litellm", specifier = ">=1.82.0,<2.0" },
     { name = "numpy", specifier = ">=1.24" },
     { name = "openai", specifier = ">=1.0.0" },
@@ -715,12 +720,8 @@ wheels = [
 
 [[package]]
 name = "gepa"
-version = "0.0.27"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/4e/99/6840f84498f2dcbfd27e8a15eeb4e637e84e9dbbd6331977b71f6ffad9c7/gepa-0.0.27.tar.gz", hash = "sha256:02ecb19e4aa6a1f5bb2994cd54b2057f25cd5e8cd662fee514303b2a8ba0a738", size = 155106, upload-time = "2026-01-28T00:33:51.72Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/a3/bd/f9e83519099a9fd5d090520ab0c51a6278e473b914a9b32d1e812662dd3b/gepa-0.0.27-py3-none-any.whl", hash = "sha256:592beb084fd638d525edae84ca75ad8e9e9c3758e5498b933c17153addf5dd2d", size = 146454, upload-time = "2026-01-28T00:33:50.262Z" },
-]
+version = "0.1.1"
+source = { git = "https://github.com/gepa-ai/gepa.git?rev=5e24ee5c8e1857a62a1ba19731de9da45ffb6f1b#5e24ee5c8e1857a62a1ba19731de9da45ffb6f1b" }
 
 [[package]]
 name = "greenlet"