Self-Reflective Chain-of-Thought (SRCoT) is a modular architecture that structures text generation as a closed Retrieve–Reflect–Revise loop, separating environment state, persistent knowledge, accumulated experience, and short-term memory into provenance-labeled stores. BM25 retrieval supplies local context, while subsequent passes expose intermediate drafts, missing-information markers, follow-up queries, and optional claim–evidence mappings to inform retrieval, revision, clarification, or abstention decisions. The authors demonstrate the approach in synthetic emergency medical and simulation scenarios, showing source-labeled documentation, explicit gap marking, and structured dispatch-style outputs, while also noting provenance-assignment errors, incomplete evidence coverage, and unsafe assumptions that persist despite prompting constraints.
arXiv:2601. 22025v2 Announce Type: replace-cross Abstract: Evaluating Large Language Model (LLM) applications differs from conventional software testing because outputs are probabilistic, semantically variable, and sensitive to prompt and model changes.
The paper demonstrates that large language models (LLMs) used to preliminarily assess medical device documentation can produce inconsistent results across different commercial deployments and settings. By constructing a fully deterministic pipeline—including OCR, chunking, embedding, indexing, retrieval, and inference—the authors achieved byte‑identical outputs across repeated runs, varied machines, and even interruptions. The study shows that end‑to‑end determinism is possible and provides a verifiable foundation for audit and change control in regulatory compliance.
arXiv:2610.08585v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here we examine the impact of a...
MemoryLACE (MemLACE) is a lightweight memory framework that explicitly models the lifecycle of textual evidence—capturing sparse merge, supersession, and contradiction relations—while preserving atomic natural‑language memories and their provenance. Unlike traditional systems that retrieve memories independently, MemLACE reconstructs relation‑aware evidence units that expose current, historical, supporting, and conflicting evidence for downstream reasoning. In benchmark evaluations (BEAM and StructMemEval) using both open‑weight and proprietary LLM backbones, MemLACE achieves the highest overall performance among same‑backbone comparisons and reduces BEAM runtime by 66.6% compared to the strongest reflective‑memory baseline, Hindsight.
arXiv:2606. 09500v1 Announce Type: new Abstract: Objective.
arXiv:2610.08364v1 Announce Type: new Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions fr...
arXiv:2606. 04990v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly solve complex tasks by interacting with external tools, retrieval systems, memory modules, environments, and other agents.
arXiv:2609.22231v1 Announce Type: new Abstract: Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories...
arXiv:2610.27816v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become the dominant paradigm for grounding the outputs of large language models (LLM) in external knowledge....
arXiv:2606. 27383v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as research assistants, yet it remains unclear whether they can calibrate research takeaways to the strength and scope of the supporting evidence.
The paper investigates whether clinical concepts are represented as distinct, causally influential centers within the latent space of large language models (LLMs). By evaluating eleven open-weight LLMs, the authors discover that each model contains dedicated clinical concept centers that are interpretable, activate only on relevant clinical narratives, and drive model behavior in both constrained and open-ended contexts. These centers can be leveraged for evaluation and performance improvement, as steering models along them enhances downstream clinical outcomes and aligns with clinician preferences.
arXiv:2508. 14817v2 Announce Type: replace-cross Abstract: Objective: To evaluate whether retrieval-augmented generation (RAG) can serve as an efficient alternative to long-context prompting for clinical reasoning over electronic health records (EHRs).