RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench.
hub
Plan-and- solve prompting: Improving zero-shot chain-of-thought reasoning by large language models
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
representative citing papers
AWARE augments generative next-POI recommendation with LLM agents that produce user-anchored narratives capturing events, culture, and trends, delivering up to 12.4% relative gains on three real datasets.
Single-agent systems with tools provide the optimal performance-efficiency trade-off for small language models, outperforming base models and multi-agent setups.
Chain-of-Thought reasoning in LLMs is often unfaithful, with models relying on it variably by task and less so as models scale larger.
LoopTrap is an automated red-teaming framework that crafts termination-poisoning prompts to amplify LLM agent steps by 3.57x on average (up to 25x) across 8 agents.
HierVA improves multi-step chart question answering by having a high-level manager maintain key joint contexts while specialized workers perform targeted reasoning with visual zoom-in.
PrismaDV generates task-aware data unit tests by jointly analyzing downstream code and dataset profiles, outperforming task-agnostic baselines on new benchmarks spanning 60 tasks, with SIFTA enabling automatic prompt optimization that beats hand-written prompts.
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
QRAFTI is a multi-agent framework using tool-calling and reflection-based planning to emulate quant research tasks like factor replication and signal testing on financial data.
A learned embedding-based router selecting among six reasoning paradigms improves LLM agent accuracy from 47.6% to 53.1% on average, beating the best fixed paradigm by 2.8pp.
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
ValuePlanner is a hierarchical architecture that uses LLMs to generate value-based subgoals and PDDL planners to produce executable actions, enabling self-directed behavior in embodied agents.
AdaPlan-H enables LLM agents to generate self-adaptive hierarchical plans that adjust detail level to task difficulty, improving success rates in multi-step tasks.
A survey that provides a taxonomy of methods for improving planning in LLM-based agents across task decomposition, plan selection, external modules, reflection, and memory.
citing papers explorer
-
RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents
RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench.
-
Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation
AWARE augments generative next-POI recommendation with LLM agents that produce user-anchored narratives capturing events, culture, and trends, delivering up to 12.4% relative gains on three real datasets.
-
Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms
Single-agent systems with tools provide the optimal performance-efficiency trade-off for small language models, outperforming base models and multi-agent setups.
-
Measuring Faithfulness in Chain-of-Thought Reasoning
Chain-of-Thought reasoning in LLMs is often unfaithful, with models relying on it variably by task and less so as models scale larger.
-
LoopTrap: Termination Poisoning Attacks on LLM Agents
LoopTrap is an automated red-teaming framework that crafts termination-poisoning prompts to amplify LLM agent steps by 3.57x on average (up to 25x) across 8 agents.
-
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning
HierVA improves multi-step chart question answering by having a high-level manager maintain key joint contexts while specialized workers perform targeted reasoning with visual zoom-in.
-
PrismaDV: Automated Task-Aware Data Unit Test Generation
PrismaDV generates task-aware data unit tests by jointly analyzing downstream code and dataset profiles, outperforming task-agnostic baselines on new benchmarks spanning 60 tasks, with SIFTA enabling automatic prompt optimization that beats hand-written prompts.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
-
QRAFTI: An Agentic Framework for Empirical Research in Quantitative Finance
QRAFTI is a multi-agent framework using tool-calling and reflection-based planning to emulate quant research tasks like factor replication and signal testing on financial data.
-
Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
A learned embedding-based router selecting among six reasoning paradigms improves LLM agent accuracy from 47.6% to 53.1% on average, beating the best fixed paradigm by 2.8pp.
-
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
-
Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents
ValuePlanner is a hierarchical architecture that uses LLMs to generate value-based subgoals and PDDL planners to produce executable actions, enabling self-directed behavior in embodied agents.
-
From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents
AdaPlan-H enables LLM agents to generate self-adaptive hierarchical plans that adjust detail level to task difficulty, improving success rates in multi-step tasks.
-
Understanding the planning of LLM agents: A survey
A survey that provides a taxonomy of methods for improving planning in LLM-based agents across task decomposition, plan selection, external modules, reflection, and memory.