## Phase 178: Autonomous Research & Agentic Scientist — Karpathy-Style Tweak Loops, Sakana-Class Tree Search, AlphaEvolve Evolutionary Discovery, Deep Research, MCTS Reasoning Substrate, Self-Play Learning, Physical-Lab Autonomy, Autoresearch Benchmarks & Governance

Sovereign replication and extension of the April-2026 frontier
autonomous-research stack. Covers Karpathy's `autoresearch` (Mar 2026, ~630 LOC)
single-GPU overnight tweak loop and its async researcher-pool successor; Sakana
AI Scientist v2 agentic tree search with VLM figure critic and peer-reviewer
ensemble; Google DeepMind AI Co-Scientist (generate / debate / evolve) and
AlphaEvolve evolutionary program search (Gemini-powered, 4×4 matmul in 48
multiplications, 23% speed-up on Gemini training kernel); OpenAI Deep Research
(o3-deep-research / o4-mini-deep-research), Perplexity / xAI / Google deep
research siblings; AIDE + MLE-Bench, SWE-agent / SWE-ReX / mini-swe-agent, Neo,
Devin, Codegen; LATS, rStar-Math, Absolute Zero Reasoner, Voyager, EvoAgentX;
PaperBench, ScienceAgentBench, DiscoveryBench, RE-Bench, HLE; Coscientist (CMU,
Nature 2023), A-Lab (LBNL), Emerald Cloud Lab, Opentrons, Strateos.

This phase is the keystone that turns Oshun from a sovereign-AI platform into a
sovereign-AI-research platform. It extends Phase 104 (Kalika theorem proving /
research agents), Phase 128 (Kalika materials discovery workbench), Phase 130
(Kalika autonomous experimentation), Phase 47 (Nous agents), Phase 98 (test-time
compute / A2A), and Phases 85–96 (training / eval / flywheel) with concrete
autoresearch scaffolding that those phases do not implement.

Tech split: Python (~55%) for agent scaffolding, sandboxed code execution, and
paper-generation tooling; TypeScript (~30%) for orchestration, dashboards, and
workbench UI; Rust (~15%) for sandbox supervisor, parallel-execution runtime,
and deterministic experiment-ledger serialisation.

Library layout: `libs/nous/autoresearch-core/`, `libs/nous/lit-graph/`,
`libs/nous/tree-search-reasoning/`, `libs/nous/self-play-loop/`,
`libs/nous/ml-engineer-agent/`, `libs/nous/tweak-loop/`,
`libs/nous/evo-search/`, `libs/nous/paper-studio/`, `libs/nous/lab-driver/`,
`libs/nous/autoresearch-evals/`, `libs/nous/autoresearch-governance/`.

---

### 178.1 Literature & Novelty Graph — `@nous/lit-graph`

#### 178.1.1 Scholarly Corpus Adapters

- [x] **178.1.1.1** Create `libs/nous/lit-graph/` with project scaffolding.
      Build Semantic Scholar Graph API adapter exposing
      `search(query, filters)`, `paper(id)`, `citations(id)`, `references(id)`,
      and the `embedding` endpoint for paper-vector nearest-neighbour novelty
      queries; exponential-backoff rate-limiting; batched bulk-fetch; local
      SQLite + MinIO cache
- [x] **178.1.1.2** Build OpenAlex adapter (300M+ records) with work / author /
      venue / concept endpoints and TSV-snapshot ingestion for offline
      full-corpus operations
- [x] **178.1.1.3** Build arXiv OAI-PMH + API adapter with daily incremental
      pull into the corpus; tie to existing `@sophia/crawling` for dedup against
      the wider web corpus
- [x] **178.1.1.4** Build Crossref, PubMed E-Utilities, CORE, and bioRxiv /
      medRxiv adapters for biomedical and multi-publisher coverage
- [x] **178.1.1.5** Build Connected Papers / Inciteful-style citation-graph
      traversal with bounded expansion budgets, dead-end detection, and
      relevance attenuation by hop distance and year

#### 178.1.2 Novelty & Prior-Art Scoring

- [x] **178.1.2.1** Build `NoveltyScorer` — given a proposed research idea
      (natural-language + keyword set), embed via Gemini-Embeddings-2 (Phase
      47.1.4) and retrieve k-nearest prior papers from `@nous/lit-graph`;
      compute a multi-component novelty score (max cosine similarity,
      second-neighbour gap, citation-graph distance from proposal's seed paper,
      publication-year spread)
- [x] **178.1.2.2** Build prior-art collision detector — flag ideas whose top-3
      neighbours exceed a similarity threshold and emit a diff explaining what
      is novel vs overlapping
- [x] **178.1.2.3** Build method / dataset / claim structured extractor
      (LLM-driven, NeurIPS-guideline-shaped) over cached papers so novelty
      queries can match at the method-granularity, not just abstract-embedding
- [x] **178.1.2.4** Build citation-quality ranking (venue tier + year + citation
      velocity + reviewer-agreement signal where available) so survey agents
      preferentially ground claims in high-quality sources

#### 178.1.3 Survey & Deep-Research Agents

- [x] **178.1.3.1** Build `ScholarQA`-class structured-survey agent producing
      citation-grounded multi-section reports with inline numbered references,
      per-section reference-quality score, and a hallucination-gate (every
      non-obvious claim must attach a paper id resolved through 178.1.1/178.1.2)
- [x] **178.1.3.2** Build STORM-class outline-then-expand survey agent with
      multi-perspective question generation and cross-referenced expansion,
      tuned for internal Oshun knowledge-bases (Sophia, Metis, Mnemosyne,
      Nisaba) in addition to public corpora
- [x] **178.1.3.3** Build deep-research agent orchestrator wrapping
      `o3-deep-research` / `o4-mini-deep-research` / Gemini Deep Research /
      Claude Research / Perplexity Deep Research as interchangeable backends
      behind a single `/research/deep` API, with per-tenant budget and
      citation-quality enforcement
- [x] **178.1.3.4** Build self-hosted deep-research baseline using `@nous/llm` +
      `@nous/lit-graph` + browse-tool + citation-critic, benchmarked against the
      external deep-research APIs on a fixed Oshun-domain query set

---

### 178.2 Reasoning & Search Substrate — `@nous/tree-search-reasoning`

#### 178.2.1 Tree / Graph Search Kernels

- [x] **178.2.1.1** Implement Language Agent Tree Search (LATS) — MCTS with PUCT
      exploration, LM value + reflection nodes, reasoning-as-planning action
      space; reproduce published 94.4% HumanEval with Oshun self-hosted model
      backbone
- [x] **178.2.1.2** Implement Tree-of-Thoughts (ToT) and Graph-of-Thoughts (GoT)
      variants as lighter-weight search patterns for cheap queries
- [x] **178.2.1.3** Implement rStar-Math — policy SLM + code-augmented MCTS +
      Process Preference Model (PPM) trained via 4 rounds of self-evolution;
      target published 90.0% MATH with Qwen2.5-Math-7B-class backbone
- [x] **178.2.1.4** Implement Reasoning-via-Planning (RAP) with
      world-model-based lookahead tying in Phase 176 RSSM / MuZero kernels for
      simulator-backed reasoning
- [x] **178.2.1.5** Build unified `SearchKernel<State, Action>` abstraction over
      LATS / MCTS / rStar / RAP, with pluggable value function, process-reward
      model, and expansion policy, reusable by every Phase 178 agent

#### 178.2.2 Process & Outcome Reward Models

- [x] **178.2.2.1** Train process-reward model via MCTS-rollout labelling on
      Oshun internal math, code, and scientific-claim datasets (Phase 89.3.1.5
      integration); use as step-level reward for search kernels
- [x] **178.2.2.2** Train outcome-reward model for code (tests-pass) and math
      (answer-verified) via executor-grounded supervision, served as shared
      reward API across Phase 178 agents
- [x] **178.2.2.3** Build reward-model drift monitor — periodically re-score
      historical high-reward trajectories, alert on silent miscalibration

---

### 178.3 Self-Improvement & Self-Play Reasoning — `@nous/self-play-loop`

#### 178.3.1 Self-Generated Curricula

- [x] **178.3.1.1** Implement Absolute Zero Reasoner (AZR, arXiv 2505.03335) —
      single model alternates proposer / solver roles generating abduction,
      deduction, induction tasks verified by a Python executor with learnability
      reward; TRR++ update; validate that training on _zero external data_
      improves baseline math/code eval
- [x] **178.3.1.2** Implement STaR / V-STaR self-taught reasoner pipelines —
      bootstrap rationales, filter by final-answer correctness, fine-tune;
      V-STaR adds verifier-filtered chain-of-thought
- [x] **178.3.1.3** Implement Self-Rewarding and Meta-Rewarding language models
      — LLM-as-judge loop producing its own DPO preference pairs, with
      meta-judge stabilising reward drift
- [x] **178.3.1.4** Implement SPIRAL-style zero-sum multi-agent self-play for
      reasoning transfer (per Phase 85.19.1.4 referenced baseline), now with
      `@nous/tree-search-reasoning` substrate underneath

#### 178.3.2 Skill Libraries & Voyager-Class Agents

- [x] **178.3.2.1** Build Voyager-class skill library — code skills indexed by
      embeddings with retrieval, composition, and iterative prompting;
      integrated with Phase 47 agent memory
- [x] **178.3.2.2** Build automatic-curriculum generator proposing progressively
      harder tasks based on current-skill coverage gap analysis (Phase 85.17.1.6
      quality-gated retraining hook)
- [x] **178.3.2.3** Build EvoAgentX-style agent-workflow evolver — mutate agent
      graphs (roles, tools, prompts, search kernels), evaluate on held-out
      autoresearch tasks, keep-the-fittest with Pareto front on quality × cost ×
      latency

---

### 178.4 Agentic ML Engineer — `@nous/ml-engineer-agent`

#### 178.4.1 AIDE-Class Tree-Search ML Engineer

- [x] **178.4.1.1** Implement AIDE (Weco, arXiv 2502.13138) — tree-search over
      Python ML code solutions, node = (code, score, diagnostics), expansion via
      LLM edits (improve / debug / diversify), beam + best-child selection;
      reproduce published MLE-Bench medal rate with Oshun self-hosted backbone
- [x] **178.4.1.2** Build sandboxed execution backend on SWE-ReX-style parallel
      shell-exec runtime (one Docker sandbox per node expansion, seccomp + user
      namespaces + per-run filesystem snapshot + wall-clock + GPU-hour budget);
      deterministic resume and replay
- [x] **178.4.1.3** Build MLE-Bench internal runner (75 Kaggle competitions,
      24h/A10 budget) wired to the agent; publish continuous leaderboard vs Neo
      (34.2%), AIDE+o1-preview (16.9%), GPT-5.3 baselines
- [x] **178.4.1.4** Build RE-Bench (METR, arXiv 2411.15114) internal runner — 7
      ML-R&D tasks with human-expert baselines — publish agent vs human frontier
      plot per task per time budget (2h / 8h / 32h)
- [x] **178.4.1.5** Build GPU-kernel autotuner agent — edits Triton / CUDA /
      PyTorch code, profiles wall-clock, verifies numerical equivalence vs
      reference; score on internal kernel library (attention, RMSNorm, rotary,
      RWKV-scan, state-space-scan)

#### 178.4.2 SWE-Bench-Class Software Engineering Agent

- [x] **178.4.2.1** Fork and extend `mini-swe-agent` / `SWE-agent` + `SWE-ReX`
      runtime; back with Claude Mythos / GPT-5.3 Codex / self-hosted
      `@iris/code` models; target ≥ 80% on SWE-Bench Verified self-test
- [x] **178.4.2.2** Build SWE-Bench Verified + SWE-Bench Pro + SWE-rebench
      (contamination-resistant) + SWE-Compass internal runners with leaderboard
      publication
- [x] **178.4.2.3** Build SWE-Lancer freelance-job harness — score agents on
      economic-value-completed-per-dollar, not just pass-rate
- [x] **178.4.2.4** Build SWE-EVO long-horizon repo-evolution harness — track
      agents over weeks-long feature-development windows with multi-PR state, CI
      signal, and review feedback integrated

---

### 178.5 Karpathy-Style Overnight Autoresearch Loop — `@nous/tweak-loop`

#### 178.5.1 Single-GPU Overnight Loop (Karpathy Pattern)

- [x] **178.5.1.1** Fork `karpathy/autoresearch` (Mar 2026, ~630 LOC) as
      reference and port to `libs/nous/tweak-loop/` adapting to Oshun
      conventions; preserve the core loop shape — agent edits a single
      `train.py`, runs a 5-minute training, reads `val_bpb` (or configured
      metric), keeps or discards based on delta, logs the decision with diff
- [x] **178.5.1.2** Build the Oshun target-training scripts — mirror
      `karpathy/nanochat` at three scales (`tweak-nano-125M`,
      `tweak-small-350M`, `tweak-mid-1B`) each with a human-authored
      `program.md` prompt, frozen `prepare.py`, and one editable `train.py`;
      validation on held-out tokens, reproducible seed
- [x] **178.5.1.3** Build multi-backend agent driver — Claude Mythos / GPT-5.3
      Codex / Gemini 3 Deep Think / self-hosted `@iris/code` as interchangeable
      code-editors with identical tooling contract; per-trial cost + latency +
      acceptance-rate reporting
- [x] **178.5.1.4** Build experiment-ledger (`@nous/tweak-loop/ledger`) —
      immutable append-only log of
      `{trial_id, parent, diff, command, metric_before, metric_after, delta, accepted, wall_clock, gpu_hours, model_rev}`;
      visualised as a tree in the autoresearch workbench
- [x] **178.5.1.5** Build `/autoresearch/overnight` one-command launcher —
      accepts `target`, `model_backend`, `budget_gpu_hours`, `max_trials`; emits
      morning summary (best delta, top-5 changes, failed-hypotheses histogram)
      to Slack / Oshun shell

#### 178.5.2 Async Researcher-Pool Orchestration

- [x] **178.5.2.1** Extend the single-agent loop to an async researcher-pool — N
      agent-workers share the experiment-ledger, branch from any ancestor, avoid
      collision via advisory locks on subtrees, and gossip accepted improvements
      forward; the design goal is Karpathy's stated "community of PhD students,
      asynchronously massively collaborative"
- [x] **178.5.2.2** Build subtree-assignment policy — UCB / Thompson sampling
      over active subtrees weighted by recent-delta and idle-time, to prevent
      N-1 agents from dog-piling the best branch
- [x] **178.5.2.3** Build merge-conflict resolver — when two branches succeed on
      orthogonal changes, automatically attempt a combined trial and accept only
      if the composition improves
- [x] **178.5.2.4** Build researcher-pool dashboard (`@nous/interp-dashboard`
      integration) — live tree view, per-agent throughput,
      cost-per-accepted-delta, hypothesis histogram, divergence metric across
      seeds

---

### 178.6 Evolutionary & Program-Synthesis Discovery — `@nous/evo-search`

#### 178.6.1 AlphaEvolve-Pattern Evolutionary Search

- [x] **178.6.1.1** Implement AlphaEvolve-pattern island model — N islands × M
      candidate programs per island, migration every k generations, LLM-driven
      mutation and crossover via Gemini 3 / Claude Mythos ensemble, evaluator
      pool running sandboxed scoring; elitism preserving per-island best
- [x] **178.6.1.2** Build canonical test bed — 4×4 matrix-multiplication
      multiplication-count (target published 48), low-rank tensor
      decompositions, sorting-network depth, bin-packing, cap-set,
      kissing-number, and GPU-kernel autotune (Phase 178.4.1.5 interop) —
      fitness deterministically machine-checkable
- [x] **178.6.1.3** Build Gemini-training-kernel optimisation harness — give the
      evolver the attention kernel source + the measured Gemini-training runtime
      benchmark; target the published ≥ 20% wall-clock improvement on equivalent
      Oshun kernels
- [x] **178.6.1.4** Build math-problem sweep — run against ≥ 50 open problems
      from the Erdős / combinatorics / analysis canon, reproducing AlphaEvolve's
      reported SOTA-match-or-beat on ~95% of the set, and log any new SOTA
      discoveries with peer-review-ready write-ups

#### 178.6.2 FunSearch-Pattern Program-of-Thought Search

- [x] **178.6.2.1** Implement FunSearch (DeepMind, Nature 2024) — evolutionary
      program search on problems with closed-form scorers; skeleton-preserving
      edits; Pareto elitism over (score, simplicity)
- [x] **178.6.2.2** Build symbolic-regression integration — route Kalika Phase
      104 symbolic-regression workloads through FunSearch for complex
      physical-law discovery benchmarks (Feynman-AI-Feynman, LLM-SR-Bench)
- [x] **178.6.2.3** Build algorithm-discovery benchmark harness with
      known-optimal landmarks, to prevent silent regression as we scale the
      evolutionary backend

---

### 178.7 Paper Drafting, Review & Replication — `@nous/paper-studio`

#### 178.7.1 Authoring Pipeline

- [x] **178.7.1.1** Build Sakana-v2-class agentic tree search paper authoring —
      stages (ideation → hypothesis → experiment design → hparam tune → ablation
      → writeup), Experiment-Progress-Manager gating promotion, buggy-node
      classifier on failed trials
- [x] **178.7.1.2** Build VLM figure critic — every generated figure passes a
      Gemini-Vision / Qwen3-VL check on caption clarity, axis labelling, unit
      hygiene, colour-blind-safe palette, and misleading-scale detection (Sakana
      v2 pattern); figures failing the critic trigger regeneration
- [x] **178.7.1.3** Build LaTeX + Typst paper-build pipeline tied to Phase 139
      scholarly-authoring stack — reproducible builds from a single YAML spec,
      deterministic bibliography, paper-embedding novelty check before emission
- [x] **178.7.1.4** Build code-artifact release pipeline — every paper emits a
      companion reproducibility bundle (Docker image, lock-file, seed,
      env-capture, wall-clock log, cost ledger), bundled and hashed into the
      Phase 111 reproducibility store
- [x] **178.7.1.5** Build plagiarism and LLM-regurgitation check — compare
      against `@nous/lit-graph` corpus and internal training-data lineage (Phase
      85.17.1.3) before publication

#### 178.7.2 Peer-Review Ensemble & Replication

- [x] **178.7.2.1** Build Sakana-v2 peer-review ensemble — 5 LLM reviewers
      prompted on NeurIPS reviewer guidelines, producing soundness /
      contribution / clarity scores and narrative comments; area-chair LLM
      aggregates into an accept / reject recommendation; target the published
      69% balanced accuracy against held-out OpenReview ground truth
- [x] **178.7.2.2** Gate every Phase 178 autoresearch-generated artefact behind
      the peer-review ensemble; artefacts below the accept threshold are flagged
      for human review or auto-revision
- [x] **178.7.2.3** Build PaperBench (OpenAI Preparedness) internal runner —
      replicate 20 ICML Spotlight papers from PDF + rubric (8,316 items),
      measure step-wise replication pass rate; publish trajectory over time
      (published human-baseline 41.4%, best current-agent 21.0% — track the
      closing gap)
- [x] **178.7.2.4** Build ScienceAgentBench (ICLR 2025, 102 tasks, 44 papers)
      internal runner — agent scientist performs data-driven discovery tasks
      end-to-end with executable deliverables
- [x] **178.7.2.5** Build DiscoveryBench (Ai2, 264 real + 903 synthetic tasks)
      internal runner — track agent discovery-rate across six disciplines over
      releases

---

### 178.8 Physical-Lab Autonomy — `@nous/lab-driver`

This extends Phase 130 (Kalika autonomous experimentation) with the specific
cloud-lab / robotic-lab driver abstractions that the bleeding edge now relies
on, and with Coscientist / A-Lab / ChemCrow integration patterns.

#### 178.8.1 Cloud-Lab & Robotic-Lab Drivers

- [x] **178.8.1.1** Build Emerald Cloud Lab driver — emit Symbolic Lab Language
      (SLL) programs, submit via ECL Command Center API, poll for completion,
      retrieve artefacts; catalogue 200+ instrument models with capability
      metadata
- [x] **178.8.1.2** Build Strateos driver — Autoprotocol emission,
      instrument-reservation API, sample-tracking; same abstraction surface as
      ECL
- [x] **178.8.1.3** Build Opentrons OT-2 / Flex driver via the Opentrons Python
      API for on-premise wet-lab automation (biology, chemistry pilot studies)
- [x] **178.8.1.4** Build unified `LabDriver` trait — `reserve(instrument)`,
      `run(protocol)`, `observe(artefactSpec)`, `log`, `abort`; Emerald /
      Strateos / Opentrons / self-hosted A-Lab drivers all conform

#### 178.8.2 Closed-Loop Scientific Campaigns

- [x] **178.8.2.1** Build Coscientist-pattern agent (CMU Gomes/Boiko,
      Nature 2023) — hardware-manual retrieval tool, protocol code-gen tool,
      reaction-planner tool, ECL / Opentrons execution; canonical integration
      test is Pd-catalysed Suzuki–Miyaura + Sonogashira cross-coupling
      optimisation
- [x] **178.8.2.2** Build A-Lab pattern (LBNL Ceder + DeepMind, Nature 2023) —
      Materials-Project candidate selector (Kalika Phase 127 hookup) + ML recipe
      generator + robotic-synthesis driver + XRD phase-identification +
      active-learning selection loop; target the published 41/58 targets in 17
      days as an internal capability benchmark
- [x] **178.8.2.3** Build ChemCrow-pattern agent (Nat Mach Intel 2024) — 18
      expert chemistry tools (molecular editors, synthesis planners, safety
      checkers) orchestrated by an LLM executive for end-to-end synthesis
      planning
- [x] **178.8.2.4** Build FAIR-Chem / UMA foundation-model integration for
      chemistry property prediction at scale inside the lab-driver planning loop
- [x] **178.8.2.5** Build Boltz-2 / AlphaFold3 / ESM3 integration for
      protein-design campaigns within `@sophia/research-engine` collaborative
      pipelines

#### 178.8.3 Safety & Dual-Use Controls

- [x] **178.8.3.1** Build wet-lab hazard classifier — every proposed protocol
      passes a controlled-substance, precursor-export, biosafety-level, and
      CWC-Schedule check before dispatch
- [x] **178.8.3.2** Build mandatory human-in-the-loop on: BSL-3+ organisms,
      Schedule 1 chemicals, CRISPR-in-germline, any high-energy reaction, or any
      protocol tagged dual-use by the classifier
- [x] **178.8.3.3** Build audit log retention and tamper-evident
      chain-of-custody for every wet-lab artefact produced by autonomous agents
      (regulatory / insurance / IP requirement)

---

### 178.9 Autoresearch Benchmarks, Observability & Experiment Ledger — `@nous/autoresearch-evals`

#### 178.9.1 Unified Benchmark Harness

- [x] **178.9.1.1** Adopt UK AISI `inspect_ai` + `inspect_evals` as the
      top-level eval harness; wire in the suites already listed (MLE-Bench,
      SWE-Bench Verified, RE-Bench, PaperBench, ScienceAgentBench,
      DiscoveryBench) plus GAIA, Cybench, CTF, and Humanity's Last Exam subsets
- [x] **178.9.1.2** Build autoresearch-specific suites: KarpathyLoopBench
      (overnight-tweak delta reproduction on a held-out `program.md` set),
      AlphaEvolveMathBench (the 50-problem open-math sweep with deterministic
      scoring), and OshunDomainBench (internal multi-domain scientific-question
      suite grounded in Veritas / Metis / Sophia / Kalika)
- [x] **178.9.1.3** Build continuous-leaderboard publisher — per-checkpoint,
      per-agent-config scores auto-posted to the Phase 91 evaluation hub with
      regression alarms and promotion gating

#### 178.9.2 Observability & Ledger

- [x] **178.9.2.1** Integrate Langfuse (OTel-native) + W&B Weave as dual
      agent-observability backends; every Phase 178 agent emits structured
      traces (parent/child span, inputs, outputs, tokens, cost, latency, tool
      calls) via a single `@nous/autoresearch-core` middleware
- [x] **178.9.2.2** Build experiments-as-first-class diffing — pick two Langfuse
      experiments, auto-compute per-prompt deltas (output, score, cost, latency,
      token usage) and render as a side-by-side report (Langfuse 2026 feature;
      own the API shape ourselves so we are not vendor-locked)
- [x] **178.9.2.3** Build the canonical experiment ledger — append-only,
      hash-chained, signed entries per trial with
      `{agent_rev, model_rev, code_diff_hash, seed, env_hash, compute_cost, wall_clock, metric_delta}`;
      ledger is the source of truth for reproducibility and audit
- [x] **178.9.2.4** Build SWE-ReX-class parallel sandbox pool as the shared
      execution substrate for every Phase 178 agent (Karpathy loop, AIDE,
      AlphaEvolve, Coscientist); sandbox isolates filesystem, network, CPU, GPU,
      and wall-clock per trial
- [x] **178.9.2.5** Extend Phase 85 data flywheel with an
      `autoresearch-outcomes` collector — ever trial's (prompt, proposed edit,
      measured delta, accepted) tuple is a high-value training example for
      improving the next generation of autoresearch agents

---

### 178.10 Multi-Agent Orchestration & Debate — `@nous/autoresearch-core`

#### 178.10.1 Generate / Debate / Evolve Multi-Agent

- [x] **178.10.1.1** Implement the Google AI Co-Scientist multi-agent pattern
      (arXiv 2502.18864) — specialised agents: Generation, Reflection, Ranking
      (Elo tournament over candidate hypotheses), Evolution, Meta-Review, and
      Proximity; scaled test-time compute controllable per query
- [x] **178.10.1.2** Build Elo-tournament ranker with LLM-judge duels,
      diversity-bonus, and anti-collusion noise injection; calibration against
      human-expert rankings on held-out hypotheses
- [x] **178.10.1.3** Validate on the published Co-Scientist case studies —
      drug-repurposing candidate proposal (liver fibrosis reference), AMR
      mechanism prediction — end-to-end within the Oshun stack

#### 178.10.2 Backbone & SDK Choices

- [x] **178.10.2.1** Build interchangeable orchestration backends (LangGraph,
      OpenAI Agents SDK, Anthropic Claude Agents, CrewAI, AutoGen, Google ADK)
      behind a single `@nous/autoresearch-core` façade; per-run selection based
      on feature coverage and cost
- [x] **178.10.2.2** Build A2A-interoperability adapter (Phase 98 integration)
      so Oshun autoresearch agents can collaborate with external third-party
      research agents under a signed capability-card exchange
- [x] **178.10.2.3** Build per-run hermetic environment — every multi-agent run
      gets a deterministic model-revision pin, tool-version pin, and
      corpus-snapshot pin; records ledger entries sufficient to replay the exact
      run months later

---

### 178.11 Governance, Safety & Compute-Budget Controls — `@nous/autoresearch-governance`

#### 178.11.1 Budget & Scope Controls

- [x] **178.11.1.1** Build per-research-run compute budget governor — global
      GPU-hours, dollar-cost, and wall-clock caps per run, per researcher, and
      per org; hard stop on breach with auto-resume-on-approval
- [x] **178.11.1.2** Build self-amplification guard — flagged any trial where
      the agent proposes self-modification of its own scaffold, budget, or
      governance code; route to human approval (Absolute Zero Reasoner
      explicitly called out this risk)
- [x] **178.11.1.3** Build distribution-shift detector on autoresearch-generated
      artefacts — alert on rapid divergence from recent validated work,
      prompting a human-in-the-loop review before publication or deployment

#### 178.11.2 Integrity & Oversight

- [x] **178.11.2.1** Build mandatory adversarial self-review pass before any
      trial is marked accepted — the agent must search its own diff for stub
      indicators (per CLAUDE.md stub list), LLM-regurgitated prior work,
      eval-contamination, and hardcoded shortcuts; only stub-free trials
      accumulate delta credit
- [x] **178.11.2.2** Build dual-use risk classifier for proposed research
      directions (bioweapon, cyber-offense, CSAM, election-interference, CBRN);
      high-risk proposals halt and escalate
- [x] **178.11.2.3** Build Kuan Yin integration (Phase 85.5) so autoresearch
      safety events feed the same moderation telemetry as user-product safety
      events, giving a single pane of glass
- [x] **178.11.2.4** Publish "Autoresearch Accountability Report" per quarter —
      trials run, accepted deltas, novel results produced, cost, safety events,
      reviewer outcomes — sovereign transparency deliverable alongside the Phase
      177 interpretability safety report

---
