IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
hub
Agentic reasoning: A streamlined framework for enhancing llm reasoning with agentic tools
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
polarities
background 4representative citing papers
KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
Iterative RAG outperforms Gold Context RAG by up to 25.6 points on ChemKGMultiHopQA across 11 LLMs, mainly by staging retrieval to avoid context overload and correct hypothesis drift.
Code Researcher retrieves global context via multi-step reasoning on code semantics, patterns, and commit history to fix Linux kernel crashes, reaching 48% crash-resolution rate versus 31% for baselines.
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
MICA combines incremental per-turn distance rewards and Monte Carlo returns from a shared potential function over user support states to create a mixed advantage signal that enables stable multi-turn RL optimization for emotional support dialogues.
RAG reaches 0.66 weighted F1 on invalid bug report subclassification while agentic web search reaches 68.9% judge success on no-code fix generation, using a new gold-standard benchmark.
Structured query and evidence tools added to an AI research agent improve benchmark accuracy by 0.6 to 3.8 percentage points.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
Agents should invoke external tools only when epistemically necessary, per the introduced Theory of Agent framework that frames tool use as a decision under uncertainty.
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.
citing papers explorer
-
IE as Cache: Information Extraction Enhanced Agentic Reasoning
IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
-
Efficient Remote KV Cache Reuse with GPU-native Video Codec
KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
-
When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
Iterative RAG outperforms Gold Context RAG by up to 25.6 points on ChemKGMultiHopQA across 11 LLMs, mainly by staging retrieval to avoid context overload and correct hypothesis drift.
-
Code Researcher: Deep Research Agent for Large Systems Code and Commit History
Code Researcher retrieves global context via multi-step reasoning on code semantics, patterns, and commit history to fix Linux kernel crashes, reaching 48% crash-resolution rate versus 31% for baselines.
-
Towards Knowledgeable Deep Research: Framework and Benchmark
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
-
MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue
MICA combines incremental per-turn distance rewards and Monte Carlo returns from a shared potential function over user support states to create a mixed advantage signal that enables stable multi-turn RL optimization for emotional support dialogues.
-
Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports
RAG reaches 0.66 weighted F1 on invalid bug report subclassification while agentic web search reaches 68.9% judge success on no-code fix generation, using a new gold-standard benchmark.
-
EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
Structured query and evidence tools added to an AI research agent improve benchmark accuracy by 0.6 to 3.8 percentage points.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
-
Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary
Agents should invoke external tools only when epistemically necessary, per the introduced Theory of Agent framework that frames tool use as a decision under uncertainty.
-
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.