The paper presents UniPPTBench and UniPPTEval, a unified benchmark and scenario-aware evaluation framework for presentation generation from vague prompts, long documents, multimodal documents, and multi-source inputs.
hub
ReAct: Synergizing reasoning and acting in language models
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 13roles
background 1polarities
background 1representative citing papers
Grid-Orch is an LLM-orchestrated system with 36 tools that lets users perform distribution grid simulations and optimizations through conversation, matching direct scripting results.
AI agent skills are reused mainly as one-time near-verbatim copies; half stay unmodified, later maintenance is additive and local, and the behavioural contract stays almost untouched.
Mining a directly-follows workflow graph from black-box conversations with an LLM agent enables structurally targeted boundary testing that covers 23–38 distinct stateful boundaries per agent, roughly doubling prompt-only baselines.
Agentic RAG-VLM achieves 78.3% success on a 12-task grasping benchmark with 360 trials per configuration, a 53.3 percentage-point gain over VLM-only baselines, via hierarchical affordance RAG, scene graph constraints, and a 14-type failure taxonomy with adaptive retry.
AB-RAG adaptively budgets retrieval in RAG by combining three confidence signals to decide when to stop or fetch more evidence, separating correct from incorrect answers at 57.6% vs 0% exact match on a factoid dataset.
pcsp is a shared RL policy using LLM persona embeddings, low-rank projection, and PPO+InfoNCE+KL training that delivers 17x above-chance zero-shot persona identification and 22x faster inference on a 300-persona benchmark.
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
LLM-driven translation of a production Rust AI agent to Python achieves near-parity on SWE-bench (73.8% vs 70.0%) and Terminal-Bench (42.5% vs 47.5%) while evolving into a 15.9x smaller superset with 30 new capabilities.
The paper defines a bounded reference architecture for LLM-orchestrated hybrid retrieval in dataset search using BM25, dense embeddings, reciprocal rank fusion, and metadata augmentation with pseudo-queries.
CAX-Agent is a three-layer agent harness for MAPDL automation whose model-driven recovery policy reaches 0.93 task completion and 0.84 zero-intervention rate on 50 simple structural benchmarks, outperforming rule-only and no-recovery baselines.
BodhiPromptShield reduces stage-wise privacy propagation in LLM/VLM agents from 10.7% to 7.1% on the Controlled Prompt-Privacy Benchmark by mediating sensitive spans before inference and restoring only at authorized boundaries.
Survey organizing LLM uses for VRP into modeler, designer, and coordinator roles, covering variants, solvers, benchmarks, and two experiments.
citing papers explorer
-
UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings
The paper presents UniPPTBench and UniPPTEval, a unified benchmark and scenario-aware evaluation framework for presentation generation from vague prompts, long documents, multimodal documents, and multi-source inputs.
-
Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics
Grid-Orch is an LLM-orchestrated system with 36 tools that lets users perform distribution grid simulations and optimizations through conversation, matching direct scripting results.
-
From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained
AI agent skills are reused mainly as one-time near-verbatim copies; half stay unmodified, later maintenance is additive and local, and the behavioural contract stays almost untouched.
-
Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
Mining a directly-follows workflow graph from black-box conversations with an LLM agent enables structurally targeted boundary testing that covers 23–38 distinct stateful boundaries per agent, roughly doubling prompt-only baselines.
-
Agentic RAG-VLM: Affordance-Aware Retrieval-Augmented Generation with Self-Reflective Planning for Robotic Grasping
Agentic RAG-VLM achieves 78.3% success on a 12-task grasping benchmark with 360 trials per configuration, a 53.3 percentage-point gain over VLM-only baselines, via hierarchical affordance RAG, scene graph constraints, and a 14-type failure taxonomy with adaptive retry.
-
AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering
AB-RAG adaptively budgets retrieval in RAG by combining three confidence signals to decide when to stop or fetch more evidence, separating correct from incorrect answers at 57.6% vs 0% exact match on a factoid dataset.
-
One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents
pcsp is a shared RL policy using LLM persona embeddings, low-rank projection, and PPO+InfoNCE+KL training that delivers 17x above-chance zero-shot persona identification and 22x faster inference on a 300-persona benchmark.
-
When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
-
From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python
LLM-driven translation of a production Rust AI agent to Python achieves near-parity on SWE-bench (73.8% vs 70.0%) and Terminal-Bench (42.5% vs 47.5%) while evolving into a 15.9x smaller superset with 30 new capabilities.
-
A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search
The paper defines a bounded reference architecture for LLM-orchestrated hybrid retrieval in dataset search using BM25, dense embeddings, reciprocal rank fusion, and metadata augmentation with pseudo-queries.
-
CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation
CAX-Agent is a three-layer agent harness for MAPDL automation whose model-driven recovery policy reaches 0.93 task completion and 0.84 zero-intervention rate on 50 simple structural benchmarks, outperforming rule-only and no-recovery baselines.
-
BodhiPromptShield: Pre-Inference Prompt Mediation for Suppressing Privacy Propagation in LLM/VLM Agents
BodhiPromptShield reduces stage-wise privacy propagation in LLM/VLM agents from 10.7% to 7.1% on the Controlled Prompt-Privacy Benchmark by mediating sensitive spans before inference and restoring only at authorized boundaries.
-
Vehicle Routing Problem Meets Large Language Models: An Overview and Perspectives
Survey organizing LLM uses for VRP into modeler, designer, and coordinator roles, covering variants, solvers, benchmarks, and two experiments.