multi-step-reasoning

Tag

Cards List
#multi-step-reasoning

Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation

arXiv cs.CL · yesterday Cached

This paper proposes SGR, a framework that enhances LLM stepwise reasoning by integrating external knowledge graphs through query-relevant subgraph generation, combining Cypher-based reasoning with collaborative reasoning integration. Experiments on CWQ, WebQSP, GrailQA, and KQA Pro show improved reasoning accuracy over standard prompting and knowledge-enhanced baselines.

0 favorites 0 likes
#multi-step-reasoning

Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation

arXiv cs.AI · yesterday Cached

This paper introduces CHARM, a framework for detecting and mitigating cascading hallucinations in multi-step agentic RAG pipelines, where early-stage errors propagate and amplify across reasoning steps. CHARM achieves an 89.4% cascade detection rate and 82.1% error propagation reduction across multiple benchmarks with low latency overhead.

0 favorites 0 likes
#multi-step-reasoning

Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval

arXiv cs.AI · yesterday Cached

This paper proposes SGDR (State-Grounded Dynamic Retrieval), an online skill learning method for web agents that enables stepwise, state-aware skill reuse rather than static task-level retrieval. Experiments on WebArena show SGDR achieves 37.5% success rate with GPT-4.1, a ~10.6% relative gain over strong baselines.

0 favorites 0 likes
#multi-step-reasoning

LLMs are not the black box you were promised

Hacker News Top · 2d ago Cached

An article summarizing Anthropic's 2025 paper on mechanistic interpretability, showing that LLMs are not black boxes and that circuit tracing can reveal multi-step reasoning and human-identifiable concepts.

0 favorites 0 likes
#multi-step-reasoning

HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models

arXiv cs.AI · 2026-05-26 Cached

This paper proposes HyperGuide, a method that distills reasoning progress into a hyperbolic geometric signal to guide step-by-step generation in LLMs, improving multi-step reasoning efficiency without explicit tree search.

0 favorites 0 likes
#multi-step-reasoning

Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)

arXiv cs.LG · 2026-05-15 Cached

This paper presents a reinforcement learning post-training pipeline for tool-calling LLM agents operating on FHIR healthcare data, achieving a 77% answer correctness on FHIR-AgentBench using a smaller Qwen3-8B model compared to 50% with o4-mini.

0 favorites 0 likes
#multi-step-reasoning

Introducing GPT-5.5 with Box

YouTube AI Channels · 2026-05-08 Cached

GPT-5.5 brings a 19 percentage point improvement in multi-step reasoning and financial modeling, significantly reducing the burden of knowledge work, which excites the Box team.

0 favorites 0 likes
← Back to home

Submit Feedback