GRIP: Grounded Reasoning via Information-Restricted Premises

• URL: http://arxiv.org/abs/2608.16776v1
• Date: Mon, 17 Aug 2026 16:23:49 GMT
• Title: GRIP: Grounded Reasoning via Information-Restricted Premises
• Abstract summary: High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant.<n>We introduce textbfGRIP, which imposes capacity asymmetry.<n>This forces the evidence channel to encode only the residual information unavailable from the query.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call this failure mode query dominance. To address it, we introduce \textbf{GRIP} (Grounded Reasoning via Information-Restricted Premises), which imposes capacity asymmetry: the decoder keeps full-dimensional access to the query, while retrieved evidence passes through a severe stochastic bottleneck. This forces the evidence channel to encode only the residual information unavailable from the query. Across five reasoning benchmarks, GRIP outperforms strong iterative baselines, cuts a query--latent mutual-information diagnostic by roughly 30$\times$ (14.8 $\to$ 0.47 bits), and reduces hallucination by 73\%. Residual-alignment analysis further shows that the bottleneck output occupies subspaces less aligned with the query than baseline representations.

Related papers

• SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs [30.494397052362384]
  We introduce SearchAtlas, a framework that converts search trajectories into structured graphs.<n>Our automated parsing pipeline achieves a mean edge F1 of 86.4% against human-annotated graphs.<n>We analyze five search agents on three benchmarks, revealing systematic differences in search scale and evidence aggregation.
  arXiv  Detail & Related papers  (2026-09-09T23:09:26Z)
• Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering [13.249024309069236]
  Hi-Q is an evidence-conditioned framework for hierarchical query refinement.<n>We evaluate Hi-Q on three multi-hop Question Answering (QA) benchmarks.
  arXiv  Detail & Related papers  (2026-08-31T08:55:07Z)
• Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos [50.28847179290796]
  PACE is a factor-guided framework for long-video evidence acquisition.<n>On MMR-V with the open-source Qwen3-VL backbone, PACE achieves 42.6% accuracy.
  arXiv  Detail & Related papers  (2026-08-26T19:38:17Z)
• Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models? [22.988311596447435]
  Visual retrieval-augmented generation (RAG) commonly expands the retrieved evidence set to improve answer-page coverage.<n>We show that this assumption does not hold for diffusion language models (DLMs)<n>We propose the Entropy-Based Candidate Filter (ECF), a training-free evidence-admission framework.
  arXiv  Detail & Related papers  (2026-08-07T09:20:40Z)
• QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards [68.15832368034815]
  We present a framework that co-designs queries and rubrics.<n>QUBRIC achieves a +5.5 point gain on ArenaHard over the SFT baseline.
  arXiv  Detail & Related papers  (2026-06-02T17:53:04Z)
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction [127.64173950476702]
  We study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools.<n>This approach requires no offline indexing and adapts naturally to evolving local corpora.<n>Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines.
  arXiv  Detail & Related papers  (2026-05-03T19:13:11Z)
• HaS: Accelerating RAG through Homology-Aware Speculative Retrieval [9.230969223605602]
  Retrieval becomes time-consuming as the knowledge databases grow in size.<n>We propose HaS, a homology-aware speculative retrieval framework.<n>Benefiting from the prevalence of queries under real-world popularity patterns, HaS achieves substantial efficiency gains.
  arXiv  Detail & Related papers  (2026-04-22T11:15:54Z)
• Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees [10.806910118253976]
  Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships.<n>We propose Query-Aware Flow Diffusion RAG (QAFD-RAG), a training-free framework that dynamically adapts graph traversal to each query's holistic semantics.<n>QAFD-RAG recovers relevant subgraphs with high probability under mild signal-to-noise conditions.
  arXiv  Detail & Related papers  (2026-04-21T08:53:34Z)
• AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing [9.271196825503417]
  Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound.<n>We present AEGIS, a novel multi-agent framework that shifts detection from ungrounded speculation to forensic verification over a closed factual substrate.<n>It reduces the false positive rate by up to 54.40% compared to leading baselines, at an average cost of $0.09 per sample without any task-specific training.
  arXiv  Detail & Related papers  (2026-03-21T04:12:04Z)
• MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries [2.756584457554517]
  Map-Disambiguate-Enrich-Reduce (MDER) generates context-derived triple descriptions and integrates them with entity-level summaries.<n>Decompose-Resolve (DR) decomposes user queries into resolvable triples and grounds them in the Knowledge Graph.<n>MDER and DR form an LLM-driven QA pipeline that is robust to sparse, incomplete, and complex relational data.
  arXiv  Detail & Related papers  (2026-03-11T18:38:44Z)
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge [50.93758649363798]
  Impliret is a benchmark that shifts the reasoning challenge to document-side processing.<n>We evaluate a range of sparse and dense retrievers, all of which struggle in this setting.
  arXiv  Detail & Related papers  (2025-06-17T11:08:29Z)
• Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner [56.08919422452905]
  We propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR) Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. We outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.
  arXiv  Detail & Related papers  (2022-05-18T21:52:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.