Tool-intent stabilization analysis quantifies when streaming RAG latency hiding is possible
A new arXiv paper introduces 'tool-intent stabilization' — the point in a streaming input at which a speculative retrieval query converges to the correct result — and measures its distribution on the CRAG benchmark (1,371 questions). The authors derive a model-agnostic bound on how much tool latency can be hidden behind remaining user input, finding that at realistic operating parameters 73.9% of queries admit substantial latency hiding. The study requires no model training and validates the bound against a working streaming pipeline, also identifying query properties that predict early versus late stabilization.
Related guides (2)
Related events (8)
Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools
This paper identifies a privacy vulnerability in tool-augmented language agents that speculatively issue future tool calls to reduce latency: these 'ghost tool calls' leak inferred user intent to external services before the agent commits to a branch, and cannot be unsent after the fact. The authors argue that timing—not authorization—is the core issue, and propose Speculative Tool Privacy Contracts, a runtime abstraction treating pre-commitment observation as a distinct first-class effect. A prototype runtime is implemented and twelve policies are evaluated across three corpora, finding that only issue-time argument or destination suppression/modification actually reduces inference leakage.
Coverage Illusion: Post-Retrieval Cascade Design Reduces LLM Augmentation Overhead in Production RAG
A case study on the Danish National Encyclopedia's RAG system evaluates five retrieval workflows across 20,000 query-workflow pairs, revealing a 'Coverage Illusion' where synthetic queries overestimate the need for LLM augmentation (90%+) versus real production traffic (27.8%). Pre-retrieval routing cannot detect this gap because augmentation necessity is only revealed after index search. A post-retrieval cascade running workflows cheapest-first and escalating to LLM augmentation only on empty results improves quality by +0.140 Composite Overall points over Always-HyDE, reduces latency by 31.8%, and eliminates LLM augmentation for 72.2% of real queries. The work highlights a structural mismatch between synthetic and real query distributions that affects RAG system design assumptions.
DocTrace: Structure-Aware On-Demand Hypergraph Memory for Long-Document QA
Researchers introduce DocTrace, a multi-agent RAG framework for long-document question answering that uses query-triggered knowledge organization rather than costly query-agnostic preprocessing. The system combines a lightweight document structural tree index, on-demand hypergraph working memory, and a graph-structured experience memory that stores successful reasoning plans for reuse. Evaluated on four long-document QA datasets, DocTrace outperforms the strongest baseline (ComoRAG) by up to 8.85% F1 and 4.40% EM while reducing computational cost by 53.32%.
UMG-RAG: Training-free hybrid retrieval with uncertainty-aware granularity fusion for long-document RAG
Researchers propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a training-free hybrid retrieval framework that addresses the tension between large and fine-grained retrieval chunks in RAG pipelines. The system converts dense and sparse retriever scores across multiple chunk granularities into evidence distributions, estimates reliability via entropy, and fuses candidates using query-specific confidence signals. A variant called UMGP-RAG uses fine-grained hits to locate evidence while returning broader parent chunks for coherence. Experiments on QA benchmarks show improved generation quality with no changes to the underlying retriever or generator.
Question-Answering as Hidden State Probing for Test-Time Reasoning Intervention
This paper proposes using question-asking as an inference-time intervention to surface information about an LLM's hidden state during chain-of-thought reasoning. The authors train a probe on a student model's hidden states before and after question generation, finding it predictive of final answer correctness even before the teacher responds—suggesting self-diagnosis during question generation carries meaningful signal. They frame question-asking as a sequential decision problem with a gating policy, but find a gap between detection and recovery: interventions are as likely to harm correct trajectories as to fix incorrect ones. The results have implications for the limits of LLM self-refinement under uncertainty.
HKVM-RAG: Hypergraph key-value separation improves multi-hop retrieval-augmented generation
A new arXiv preprint introduces HKVM-RAG, an evidence-organization layer for multi-hop RAG that uses weighted hyperedges as retrieval keys while retaining passage text as answer values. Under a fixed-substrate protocol controlling for tuple cache, reader, and evaluation budget, the hypergraph key-value approach improves over KG-PPR by +3.4 F1 on 2WikiMultiHopQA and +3.6 F1 on MuSiQue. A dense-aware controller combining frozen ColBERTv2 with HKVM features reaches 88.8, 65.1, and 85.8 F1 on three benchmarks, outperforming ColBERTv2 alone by 5–11 F1 points. The work positions hypergraph organization as a reusable evidence-control mechanism rather than a dense-retrieval replacement.
Probe-and-Refine Tuning improves coding agent performance via iterative repository guidance refinement
A new arXiv paper introduces probe-and-refine tuning, a procedure that uses synthetic bug-fix probes to iteratively improve AGENTS.md repository guidance files for LLM-based coding agents without requiring an agent loop during tuning. Evaluated on SWE-bench Verified with Qwen3.5-35B-A3B, the method achieves 33.0% mean resolve rate versus 28.3% for a static knowledge base baseline and 25.5% for an unguided baseline. The improvement is attributed to coverage gains—refined guidance helps agents locate the correct files rather than improving patch quality—and a step-budget experiment shows guidance is necessary for agents to productively use larger compute budgets.
Anthropic introduces Contextual Retrieval to reduce RAG retrieval failures by up to 67%
Anthropic published a technical method called Contextual Retrieval that combines Contextual Embeddings and Contextual BM25 to address the context-loss problem in traditional RAG pipelines. The approach prepends chunk-level context before encoding, reducing failed retrievals by 49% standalone and 67% when combined with reranking. The post also highlights prompt caching as a simpler alternative for knowledge bases under 200K tokens, and provides a cookbook for deployment with Claude.