Apodex

Meet 𝗔𝗽𝗼𝗱𝗲𝘅 𝟭.𝟬 🔭 — a heavy-duty agent team for deep research, which sets the SOTA! The team searches the web, reasons over evidence, and writes reports where every claim is backed by an explicit 𝘦𝘷𝘪𝘥𝘦𝘯𝘤𝘦 𝘤𝘩𝘢𝘪𝘯, independently audited before delivery. 🌐 apodex.ai

@harshitagu72595 Yes, and confidently wrong is truly worth designing against.

@Apodex_AI A great reminder that confidence and accuracy aren’t the same thing.

We handed Apodex 1.0 and six frontier models one trivia question with a trap built in. Among Nobel Literature laureates, which ones were formally expelled by their own government ? +1 per correct name, −1 per name that misses the bar. The biggest names kept adding names, straight into negative scores. 🧵

Apodex has released Apodex 1.0, a verification-centric deep research agent that searches the web, synthesizes evidence, and generates reports in which every claim is backed by an auditable chain of evidence. In heavy-duty mode, Apodex 1.0-H runs an async team of up to 150 sub-agents, with a global verifier checking the assembled evidence before any answer is committed. Evidence over generation 👀

The over-claiming you just watched is the same reflex that invents a fake citation, a wrong dosage, a number that isn't in the filing. These models reached for the plausible-looking answer. Apodex is a self-evolving heavy-duty solver built to verify before it delivers — for the work where one wrong line has real cost.🔭

Same question, six frontier models. The Over-claimed column👇

Apodex 1.0 dropped and the architecture is genuinely different. It's post-trained on Qwen3.5 as a self-evolving system: math, coding, and general knowledge stay intact while deep-research ability compounds over time. No catastrophic forgetting. That balance is harder to build than it sounds. The heavy-duty side: the 1.0-H model runs up to 150 sub-agents in parallel, all exploring the web simultaneously. A separate verification layer audits every claim before the final report assembles. Not just search plus summarize. There's actual conflict resolution baked into the pipeline. Numbers: BrowseComp 90.3, DeepSearchQA 94.4, HLE-text 60.8. SOTA across open and closed source right now. The part worth sitting with: their 4B mini model beats every 30B-class open model on BrowseComp and DeepSearchQA. Smaller, cheaper, better at research. The scaling story is quietly shifting. Underneath all of it is AgentOS, a task-agnostic runtime handling scheduling, routing, checkpoints, and cost accounting. Workflow logic sits in plugins above it, so adding a new app is just a folder of code. Open weights too. Worth a look if you're building research pipelines or thinking about how agent orchestration should actually be structured.

Predicting the future takes deep research. Great to see Apodex-1.0-mini rank first again on FutureX：futurex.live Try it here: apodex.ai

As a self‑evolving heavy‑duty solver, the Apodex family reliably converts cryptic clues into a verifiable identifier rather than a plausible‑sounding fabrication. If you work in a high-stakes domain, be our eval and throw your hardest problems at Apodex! #AIforScience

Here’s how six frontier models performed: −4: GPT‑5.4 (Zytiga), Qwen3.6‑Plus (invented “Zurnai”), GLM‑5.1 (none), MiniMax‑M2.7 (none) +4: Claude‑Opus‑4.7, Gemini‑3.1‑Pro Two baselines matched the ground truth on all four fields. The other four finished at −4 through confident mistakes, hallucination, or no answer. Apodex matches frontier-level accuracy with a 35B model and an architecture that exposes the evidence and exclusion logic you can audit. 🤏 🦾

Apodex-1.0-mini, our 35B model, currently holds the #1 spot on the FutureX. But leaderboards are sanitized: clean queries, no penalty for confident wrong answers. So we wrote one deliberately brutal question: four facts to recover, a scoring rule where confident but wrong = −4, correct = +4. Between frontier models and Apodex, here’s what happened. 🧵👇

@csaba_kissi A research team you can spin up on demand.

@Apodex_AI It's like having an entire department of researchers.

Meet 𝗔𝗽𝗼𝗱𝗲𝘅 𝟭.𝟬 🔭 — a heavy-duty agent team for deep research, which sets the SOTA! The team searches the web, reasons over evidence, and writes reports where every claim is backed by an explicit 𝘦𝘷𝘪𝘥𝘦𝘯𝘤𝘦 𝘤𝘩𝘢𝘪𝘯, independently audited before delivery. 🌐 apodex.ai

Apodex-1.0 @Apodex_AI just dropped! Self-evolving heavy-duty solver. 150 agents across 15,000 steps. Independent verification on every attempt. SOTA on BrowseComp, FrontierScience, SuperChem. Open weights available. Check it out: apodex.ai

Apodex-1.0 @Apodex_AI changed deep-research AI with a self-evolving heavy-duty solver. It coordinates 150 agents across 15,000 steps. Verifies through independent auditors. Improves each attempt by critiquing the last. Built for research problems that have no existing answer. A step-by-step guide 🧵 👇

This Delaware scenario is just one instance. Law, life sciences, clinical Medicine, finance, compliance, critical engineering: the cost of hallucination is real. We built Apodex for a simple reason: deep research agents should not only find answers, but prove why those answers are right. Link in bio. Give it a spin and tell us how it went.🦾 #LegalTech

Apodex is a Self‑Evolving Heavy‑Duty Solver built exactly for this: • Retrieval + verification agents run in parallel, routing everything through a shared evidence pool • A global verifier reasons over the assembled evidence graph, weighing the support behind each claim • A verification gate sends the answer back whenever citation coverage or evidence support falls short →Every claim in the final report traces back to a source you can open. Full audit trail.

In Mississippi, a federal judge just threw all 4 lawyers — both sides — off a case for “blindly relying on technology.” In Oregon, one team submitted AI‑hallucinated case citations. Penalty: $109,700 + the case got tossed. 🧵👇