Skip to content

BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence

Sep 2026 · 0 citations · 41 references
Computer Science

TL;DR

BELIEFRAG is introduced, a closed-loop controller that updates an explicit state over sufficiency, reliability, conflict, uncertainty, evidence gaps, and acquisition cost, then chooses among retrieval, query rewriting, verification, answering, stopping, and abstention.

Abstract

Adaptive RAG uses signals such as confidence, relevance, support, and retrieval quality to decide when to search or correct evidence. In multi-step retrieval, however, these local signals must be combined into a persistent view of what the current evidence supports, what remains missing, and which action should follow. Existing methods often use such signals as separate triggers, making it difficult to preserve a coherent evidence state across a trajectory; we call this problem evidence-state fragmentation. We introduce BELIEFRAG, a closed-loop controller that updates an explicit state over sufficiency, reliability, conflict, uncertainty, evidence gaps, and acquisition cost, then chooses among retrieval, query rewriting, verification, answering, stopping, and abstention. Across six QA benchmarks with gpt-oss-120b, BELIEFRAG reaches mean token F1 0.572 with 3.89k tokens per question, outperforming fixed iterative retrieval (0.555 F1) while using 39% fewer tokens. The same quality-cost pattern transfers to Qwen3-32B, where BELIEFRAG reaches 0.552 F1 versus 0.523 for iterative retrieval while using 35% fewer tokens. Analysis shows that the main gains come from corrective re-retrieval rather than pruning alone, while several belief dimensions are redundant and calibrated answerability plays the strongest operational role. Calibration improves threshold stability across related evidence sources, although source shift can still invalidate the same decision signal.

View source

Similar papers

STAR: Structure-Aware Adaptive Retrieval for RAG

STAR is presented, a structure-aware adaptive retrieval framework for RAG that treats this mismatch as a problem of diagnosing evidence sufficiency and benefits from a control signal that preserves structurally distinct insufficiency patterns rather than collapsing them into a single scalar confidence estimate.

Yeowon Jeon, Chong-kwon Kim, Y. Choi · 0 citations
Preprint Aug 2026

From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents

Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurrence coverage, or must discriminate competing hypotheses---which can cause failure before substantive reasoning begins. Prescribing a fine-grained solution procedure for...

Can-Can Zhang, Bao-Feng Zhang, Xiao-Tian Han et al. · 0 citations
Preprint Aug 2026

Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay

Interactive language-model agents use confidence signals to decide whether to answer immediately, retrieve additional evidence (from memory or external knowledge), or defer. Yet confidence is usually evaluated in isolation, without measuring the trajectory-level consequences of the actions it triggers. We propose match...

Prateek Chhikara · 3 citations
#artificial intelligence Preprint Oct 2026

RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation

Following retrieved evidence does not guarantee factual correctness: misleading evidence can induce a model to replace an answer it previously gave correctly. Standard accuracy measures obscure this behavior by combining answer replacement with preexisting errors. We introduce RAG-Stress, a controlled diagnostic protoc...

Shun-Yuan Zhou, Hao Chen, Tian-Yu Wang et al. · 1 citation
#machine learning Preprint Oct 2026

Grounded Credit Assignment in Reinforcement Learning for Multi-Turn Search Agents

GCA is proposed, which uses verifiable sub-outcomes (evidence retrieval and answer correctness) to correct search and answer credit separately: a wrong answer is blamed more than the search that found the evidence, and a correct answer that bypasses retrievable evidence is credited less.

Qi-Rui Liu, Hao Chen, Yi Wen et al. · 1 citation
#artificial intelligence Conference Open access Sep 2026

Self-Reports Are Not Verification

An environment-grounded audit is introduced in which every intermediate proposal receives an exact outcome in an evolutionary Contexto search whose feedback function assigns every valid guess an exact rank without human annotation.

En-Rong Pan, Ryan Zhou, Ting Hu · 0 citations

Related blog posts

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