SkillEvolBench is a new diagnostic benchmark that evaluates the transition from episodic experience to procedural skills in LLM agents using role-conditioned task families and frozen deployment tests.
hub
React: Synergizing reasoning and acting in language models
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
RobotEQ is a new benchmark dataset and evaluation suite showing that current embodied AI models fall short on active social-norm compliance, especially spatial grounding, though RAG with external knowledge helps.
EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
APWA is a distributed multi-agent architecture that decomposes parallelizable agentic workflows into non-interfering subproblems for scalable execution on heterogeneous resources.
VPR converts symbolic, constraint, or posterior oracles into dense turn-level rewards for RL, improving credit assignment in agentic reasoning and transferring to general benchmarks.
Swarm Skills is a portable multi-agent coordination specification with roles, workflows, bounds, and a self-evolution algorithm that distills trajectories using Effectiveness, Utilization, and Freshness scores for zero-adapter portability.
Kintsugi learns policies by repairing composable executable knowledge bases through agentic diagnosis, localized typed edits, and deterministic verification gates that admit only improvements.
EvoMAS trains a workflow adapter with policy gradients to dynamically instantiate stage-specific multi-agent workflows from a fixed agent pool, using explicit task-state construction and terminal success signals, and outperforms static baselines on GAIA, HLE, and DeepResearcher.
TRUSTEE uses an 8B LM to simulate complete dynamic environments for RL-based tool learning and outperforms baselines that require extra external resources.
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
An LLM agent integrated with AVEVA Process Simulation via MCP enables natural language driven flowsheet analysis, optimization, and construction for chemical separation processes.
SiRA uses LLM world models for simulative reasoning to achieve up to 124% higher task completion and 32.2% navigation success versus reactive baselines in web environments.
citing papers explorer
-
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
SkillEvolBench is a new diagnostic benchmark that evaluates the transition from episodic experience to procedural skills in LLM agents using role-conditioned task families and frozen deployment tests.
-
RobotEQ: Transitioning from Passive Intelligence to Active Intelligence in Embodied AI
RobotEQ is a new benchmark dataset and evaluation suite showing that current embodied AI models fall short on active social-norm compliance, especially spatial grounding, though RAG with external knowledge helps.
-
Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
-
APWA: A Distributed Architecture for Parallelizable Agentic Workflows
APWA is a distributed multi-agent architecture that decomposes parallelizable agentic workflows into non-interfering subproblems for scalable execution on heterogeneous resources.
-
Verifiable Process Rewards for Agentic Reasoning
VPR converts symbolic, constraint, or posterior oracles into dense turn-level rewards for RL, improving credit assignment in agentic reasoning and transferring to general benchmarks.
-
Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering
Swarm Skills is a portable multi-agent coordination specification with roles, workflows, bounds, and a self-evolution algorithm that distills trajectories using Effectiveness, Utilization, and Freshness scores for zero-adapter portability.
-
Kintsugi: Learning Policies by Repairing Executable Knowledge Bases
Kintsugi learns policies by repairing composable executable knowledge bases through agentic diagnosis, localized typed edits, and deterministic verification gates that admit only improvements.
-
EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems
EvoMAS trains a workflow adapter with policy gradients to dynamically instantiate stage-specific multi-agent workflows from a fixed agent pool, using explicit task-state construction and terminal success signals, and outperforms static baselines on GAIA, HLE, and DeepResearcher.
-
Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
TRUSTEE uses an 8B LM to simulate complete dynamic environments for RL-based tool learning and outperforms baselines that require extra external resources.
-
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
-
Large Language Model Agent for User-friendly Chemical Process Simulations
An LLM agent integrated with AVEVA Process Simulation via MCP enables natural language driven flowsheet analysis, optimization, and construction for chemical separation processes.
-
General Agentic Planning Through Simulative Reasoning with World Models
SiRA uses LLM world models for simulative reasoning to achieve up to 124% higher task completion and 32.2% navigation success versus reactive baselines in web environments.