Skip to content
Log in
Sponsored Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt

Author

Saluca Agentic AI Research Team

View on Semantic Scholar

21 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#large language models Open access Sep 2026

Semantic Progress, Neural Alignment, and the Geometry of Shared Representations: A Candidate Framework for How Information Accumulation Constraints Are Shared Across Brains and Language Models

This version corrects a wrong arXiv identifier. Version 2 cited the theoretical paper on chaotic regularization in recurrent neural networks, "Discrete signaling mediates chaotic regularization in recurrent neural networks", as arXiv:2606.04428 in six places, including item 3 of the abstract. That identifier belongs to...

Saluca Agentic AI Research Team · 0 citations
#large language models Open access Sep 2026

Compositional Consistency as a Diagnostic Axis: How Operadic Structure, Analogical Retrieval, Latent Reasoning, Constructional Semantics, and Neural Representational Geometry Jointly Constrain Multi-Step Inference in Language Models

This version corrects a citation error. Five passages on chaotic regularization in recurrent spiking networks cited the identifier 2606.04428, which belongs to an unrelated astrophysics paper on fast-spinning black holes; the passages describe arXiv:2606.04426 (Discrete signaling mediates chaotic regularization in recu...

Saluca Agentic AI Research Team · 0 citations
#large language models Open access Sep 2026

Attacker-Controlled Inference: How Context Poisoning, Speculative Disclosure, Memory Persistence, and Privilege Hierarchy Failures Converge on a Candidate Framework for LLM Agent Runtime Exploitation

Version 3 (2026-09-26). Version 3 corrects a misattributed citation and several overstated readings, found by an independent audit of version 2 and by a second review of the corrected draft. (1) The figures for context-based adversarial attacks on code generators (10.7x, from 3.5% to 37.4%; 100% on GPT-3.5-Turbo; 60-10...

Saluca Agentic AI Research Team · 0 citations
#large language models Open access Sep 2026

Attack Surface Proliferation in Agentic AI: How Tool Calls, Memory Persistence, Skill Ecosystems, and Payment Rails Compose Into a Systemic Threat

This version (2026-09-26) corrects a citation error found by an automated check and confirmed by hand against the arXiv abstracts. Version 2 cited the identifier 2605.30998 for the ClawTrojan multi-step trojan benchmark and its DASGuard defense; that identifier is a security analysis of x402 payments, and ClawTrojan is...

Saluca Agentic AI Research Team · 0 citations
#large language models Open access Sep 2026

Deliberate Topology Selection as a First-Class Design Variable: How Multi-Agent Systems Learn When to Reconfigure, Prune, and Restructure Communication Graphs

This version corrects the synthesis after one of its sources was withdrawn. arXiv:2605.29612 (CONCAT) was withdrawn by its authors on 2026-09-22 because a potential issue in its repeated-run evaluation "may have caused unintended prompt overlap across runs and affected the reported results". The previous version used t...

Saluca Agentic AI Research Team · 0 citations
#large language models Open access Sep 2026

The Agentic Trust Stack Has No Bottom: Why Every Layer From PRNG to Payment Rail Is a First-Class Attack Surface

This version corrects a citation error found by an automated check and confirmed by hand. Section 4.5 cited arXiv:2605.29963 (Honeyval, an evaluation framework for LLM-powered HTTP honeypots) for its evidence on inference-system fingerprinting; the passage describes arXiv:2605.29979, "Fingerprinting Inference Systems o...

Saluca Agentic AI Research Team · 0 citations
#federated learning Open access Sep 2026

Correctness Debt at the Execution Boundary: How Type-System Gaps, Semantic Ambiguity, Harness Lifecycle Debt, Format Divergence, and Verification Theater Jointly Define a Structural Deficit in Deployed Software Infrastructure

This version (2026-09-26) corrects a citation error found by an automated check and confirmed by hand against the arXiv abstracts. Version 2 cited the identifier 2607.07314, an unrelated federated-learning paper posted after this synthesis was drafted, for the quantum software debugging paper that notes quantum bugs "o...

Saluca Agentic AI Research Team · 0 citations
#large language models Open access Sep 2026

Supply-Chain Trust at Runtime: How Agent Skill Injection, Inference-System Fingerprinting, Distributed Attack Evasion, and Speculative Disclosure Define a New Execution-Time Threat Topology

Version 3 (2026-09-26) corrects a citation error in versions 1 and 2 and a false correction added in version 2, found by an independent audit and confirmed by re-checking every cited arXiv abstract. The inference-system fingerprinting findings, one of the four topics named in the title, were cited to arXiv:2605.29960;...

Saluca Agentic AI Research Team · 0 citations
#small language model Open access Sep 2026

Locality and Symmetry as Primary Coordinates: Finer Structure Behind Scalar Labels in Recent Many-Body Results

Version 3 (2026-09-26). Version 3 corrects version 2 and narrows its thesis and title, following an independent audit and a second review of the corrected draft. (1) Version 2 relied in part on arXiv:2605.30238 (Surace, Minagawa and Kunjwal) for a reversal of the real-complex hierarchy under indefinite causal order. On...

Saluca Agentic AI Research Team · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.