arXiv AI
Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 12
Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells
The study investigates whether independently trained language‑model societies share a common packet language and how inherited interface states affect learning. A comprehensive audit of 30 pairwise interactions among six restricted societies shows that only one pair is fully interoperable, another is partially compatible, and the remaining 26 pairs fail across all alignment levels. Further experiments reveal that a globally trained communication interface can act as a severe negative‑transfer prior, but inherited interfaces never outperform fresh‑interface controls by the preregistered margin.
Hugging Face Trending Papers
Sep 10
Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells
The study investigates whether independently trained language‑model societies share a common packet language and how inherited interface states affect learning. A comprehensive audit of 30 pairwise interactions among six restricted societies shows that most cross‑initialization pairs fail to interoperate, with only one pair achieving full bidirectional compatibility. Further experiments reveal that reinitializing only the packet reader, writer, and mouth dramatically improves accuracy, while inherited interfaces never outperform fresh ones by the preregistered margin.
arXiv Machine Learning
Jun 5
Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models
arXiv:2606. 05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families.
arXiv Machine Learning
Aug 18
Architecture-Dependent Causal Transfer of Activation States Across Large Language Models
arXiv:2608. 16347v1 Announce Type: cross Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency.
arXiv AI
Sep 10
VST: Verifiable Structured Transport for Auditable Agent-to-Agent Alpha Discovery
arXiv:2609.07065v1 Announce Type: new Abstract: Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation agents, whose hand-offs, in contemporary LLM m...
arXiv AI
Jul 14
StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
arXiv:2607. 11388v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use.