Issues

• eval(agentmembench): track AgentMemBench retrieval-only AutoMem adapter [LOW PRIORITY]

  enhancement
  verygoodplugins/automem-evals#86 · Filter by author autojack-bot opened on Nov 5, 2026

• Bench Meilisearch as a retrieval backend for AutoMem (keyword leg first, vector leg second)

  verygoodplugins/automem-evals#83 · Filter by author autojack-bot opened on Nov 4, 2026
  1

• eval(memsyco): memory-use authority and sycophancy track

  verygoodplugins/automem-evals#76 · Filter by author autohub-codex opened on Oct 25, 2026

• eval(feb30): intrinsic store-state adapter (blocked on official release)

  verygoodplugins/automem-evals#74 · Filter by author autohub-codex opened on Oct 24, 2026

• track: StreamMemBench streaming evidence-use/feedback-reuse eval (arXiv:2606.14571, EMNLP 2026 Findings)

  verygoodplugins/automem-evals#67 · Filter by author autohub-codex opened on Oct 18, 2026
  1

• chore(eval): refresh shared experiment dashboard with historical artifacts

  verygoodplugins/automem-evals#65 · Filter by author autohub-codex opened on Oct 11, 2026
  1

• eval(precisionmembench): retrieval-precision adapter for AutoMem

  verygoodplugins/automem-evals#64 · Filter by author autohub-codex opened on Oct 11, 2026
  2

• eval(veracium): longitudinal validity-interval + provenance/injection eval

  verygoodplugins/automem-evals#62 · Filter by author autohub-codex opened on Oct 9, 2026
  4

• eval(atma): track LTP ghost-memory benchmark (blocked on public artifacts)

  verygoodplugins/automem-evals#57 · Filter by author autohub-codex opened on Oct 4, 2026

• track: LongMemEval-V2 web-agent experience benchmark

  verygoodplugins/automem-evals#54 · Filter by author autohub-codex opened on Oct 2, 2026

• eval(merit): action-producing, cost-aware AutoMem adapter

  verygoodplugins/automem-evals#53 · Filter by author autohub-codex opened on Oct 2, 2026

• eval(memtrace): evidence-use diagnostic adapter (blocked on public artifacts)

  verygoodplugins/automem-evals#51 · Filter by author autohub-codex opened on Oct 2, 2026
  2

• StateMemBench: current vs superseded state eval

  verygoodplugins/automem-evals#50 · Filter by author autohub-codex opened on Oct 1, 2026
  3

• eval(protocol): execute MemDelta-controlled AutoMem baselines on LongMemEval-S and Mem2ActBench

  verygoodplugins/automem-evals#48 · Filter by author jack-arturo opened on Sep 30, 2026

• GAM hierarchical graph memory: architecture comparison + LoCoMo-50 eval

  verygoodplugins/automem-evals#33 · Filter by author jack-arturo opened on Sep 18, 2026

• MemoryAgentBench (ICLR 2026): 4-competency incremental multi-turn eval

  verygoodplugins/automem-evals#32 · Filter by author jack-arturo opened on Sep 18, 2026

• ForgetEval / ForgetEval-Adv: control-plane forgetting (supersede/release/purge) eval

  verygoodplugins/automem-evals#31 · Filter by author jack-arturo opened on Sep 18, 2026
  4

• MemoryCD (ICLR 2026 workshop): cross-domain personalization eval for AutoMem relation linking

  verygoodplugins/automem-evals#30 · Filter by author jack-arturo opened on Sep 18, 2026

• AML Cycle 2: AutoMem adapter readiness (opens 2026-09-20)

  verygoodplugins/automem-evals#28 · Filter by author jack-arturo opened on Sep 18, 2026
  5

• AutoMem: AMA-Bench eval adapter + ICML 2026 leaderboard submission

  verygoodplugins/automem-evals#27 · Filter by author jack-arturo opened on Jun 29, 2026
  2

• AutoMem vs PlugMem: knowledge-centric graph architecture comparison + eval run

  verygoodplugins/automem-evals#26 · Filter by author jack-arturo opened on Jun 29, 2026

• feat(automem): Evaluate AutoMem against PersonaMem-v2 — DCPM gap analysis

  verygoodplugins/automem-evals#25 · Filter by author jack-arturo opened on Jun 29, 2026

• feat(automem): Evaluate against Mem2ActBench — proactive tool-calling memory (arXiv:2601.19935)

  verygoodplugins/automem-evals#24 · Filter by author jack-arturo opened on Jun 29, 2026
  2

• feat(automem): FAMA evaluation harness — measure forgetting-aware accuracy against Memora benchmark (ACL 2026)

  verygoodplugins/automem-evals#22 · Filter by author jack-arturo opened on Jun 27, 2026
  1

• Cold vs matured benchmark methodology (maturation-v1): simulate consolidation/decay on the narrative clock

  verygoodplugins/automem-evals#18 · Filter by author jack-arturo opened on Jun 16, 2026
  1