Research
Public arXiv preprints across the full Qualixar umbrella — memory, assertions, evaluation, security, and orchestration. Every benchmark reproduces. Every claim has a source.
Preprints on arXiv — not peer reviewed. Code, scoring protocols and preregistration ship alongside the papers.
ResearcharXiv · Aug 2026cs.SEcs.AI
Bounded Loops: Pre-Run Spend Bounds, Proved Termination, and Verified Completion for Agent Harnesses
Varun Pratap Bhardwaj, Garima Singh, Arun Pratap Bhardwaj
The instrument found 47 vacuous gates — checks satisfied by the absence of the thing they check — in shipped, reviewed code
In mainstream agent frameworks a step ends when the agent's own output says it has finished. This paper states what a harness must instead guarantee — that it finishes, does not drift, and does not overspend — and proves each one: termination in closed form under a global repair budget, no DONE without a gate verdict in an append-only hash-chained ledger, and a spend ceiling enforced inside an attempt rather than between attempts. It then builds the instrument that measures whether a harness delivers it, characterising two ways a sound-looking check passes anything: vacuity and self-attestation. Engine, catalogue and corpus are Apache-2.0.
ReliabilityarXiv · Aug 2026cs.AIcs.MA
Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence
Varun Pratap Bhardwaj, Garima Singh, Arun Pratap Bhardwaj
Two instances of the same model failed together on 90% of missions where either failed — independence is not a safe assumption
Multi-agent reliability analysis routinely assumes component failures are conditionally independent, and almost never tests it. This paper tests it and finds strong positive dependence, which inflates joint failure rates well beyond what independence-based bounds predict. It replaces the assumption with a certificate that assumes no dependence structure at all — a linear program over the joint distribution, bounded by a Bonferroni–Clopper–Pearson box — and proves that fitting a dependence model instead degrades coverage as sample size grows.
MemoryarXiv · Aug 2026cs.AIcs.IR
SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents
Varun Pratap Bhardwaj, Garima Singh, Arun Pratap Bhardwaj
Governed memory with scoped component evidence and disclosed negative results
The revised preprint studies governed local-first memory and distinguishes implementation from verified effectiveness. Component evidence is protocol-scoped; current package behavior requires separate checks.
Agent OSarXiv · Apr 2026cs.AIcs.MAcs.SE
Qualixar OS: A Universal Operating System for AI Agent Orchestration
Varun Pratap Bhardwaj
One universal port for AI agents — 12 topologies, POMDP routing, four-tier degradation
Every agent framework reinvents orchestration, and none of them interoperate. Qualixar OS defines a universal substrate — a topology catalogue, POMDP-based routing between agents, and a four-tier degradation ladder that keeps a system answering when parts of it fail.
MemoryarXiv · Apr 2026cs.AIcs.CLcs.IR
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
Varun Pratap Bhardwaj
Forgetting as a feature — biologically-inspired decay, cognitive quantization, multi-channel retrieval, zero LLM calls
A memory system that never forgets degrades: old facts crowd out current ones and retrieval quality falls. V3.3 borrows the brain's answer — decay curves, consolidation, and quantized cognitive states — and retrieves across six independent channels fused by reranking, without a single LLM call in the hot path.
MemoryarXiv · Mar 2026cs.AIcs.IRcs.LG
SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory
Varun Pratap Bhardwaj
74.8% on LoCoMo with zero cloud calls — the highest local-first score reported
Retrieval quality is usually bought with LLM calls. V3 buys it with geometry instead: memories live on a statistical manifold where relevance is a distance, so ranking is computed rather than generated. The result is a benchmark score competitive with cloud systems, produced entirely on-device.
EvaluationarXiv · Mar 2026cs.AIcs.SE
AgentAssay: Token-Efficient Regression Testing for Non-Deterministic AI Agent Workflows
Varun Pratap Bhardwaj
Regression testing that treats non-determinism as the subject, not the obstacle — 5–20x cost reduction
You cannot diff an agent's output against a golden file, because the output legitimately differs every run. AgentAssay tests the distribution instead of the sample: stochastic verdicts over repeated runs, with a sampling strategy that reaches a decision in a fraction of the tokens a naive repeat-and-compare would burn.
SecurityarXiv · Feb 2026cs.CRcs.AIcs.SE
Formal Analysis and Supply Chain Security for Agentic AI Skills
Varun Pratap Bhardwaj
Agent skills execute with your agent's full privilege and nobody checks them — 675 tests, 8 novel contributions
An agent skill is arbitrary code that runs with the agent's own authority, installed from a registry with no review gate. This paper gives the threat model a formal treatment, then builds static analysis, provenance verification and SBOM generation across 22 agent frameworks so a skill can be judged before it executes.
ReliabilityarXiv · Feb 2026cs.AIcs.MAcs.SE
Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents
Varun Pratap Bhardwaj
Design-by-contract for agents — invariants that hold on every execution path. 1,980 sessions across 7 models
Prompts express intent; they do not enforce it. This paper adapts design-by-contract to autonomous agents: preconditions, postconditions and invariants stated formally, then checked at runtime, so a violation is caught at the step that caused it rather than three tool calls downstream.
MemoryarXiv · Feb 2026cs.AIcs.CR
SuperLocalMemory: Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory Poisoning
Varun Pratap Bhardwaj
Shared memory is an attack surface — Bayesian trust scoring that degrades a poisoned writer instead of trusting it
When several agents write to one memory store, a single compromised agent can poison what every other agent later recalls. This paper models writer trust as a Bayesian posterior updated by downstream outcomes, so a source that keeps producing facts which fail verification loses influence over retrieval — without any of the data leaving the machine.
Citing Our Work
If you use any Qualixar tool or finding in your research, please cite the corresponding paper. Every card above has a one-click BibTeX entry; canonical entries are also on each arXiv page.