CurateEvo evolves executable data-curation code using failed agent trajectories, improving post-training performance by 3.2 and 2.7 points over baselines on labeled and wild data respectively.
Trial and error: Exploration- based trajectory optimization of LLM agents
7 Pith papers cite this work, alongside 18 external citations. Polarity classification is still indexing.
7
Pith papers citing it
18
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Evoflux applies evolutionary search at inference time to repair executable tool workflows for compact agents, outperforming SFT and SFT+DPO on held-out MCP-Bench tasks with live servers and 250 tools.
COMAP co-evolves textual world models and agent policies for LLMs through on-policy self-distillation, yielding up to 16.75% relative gains on embodied planning, web navigation, and tool-use tasks.
ACT*ONOMY is a Grounded-Theory-derived hierarchical taxonomy and open repository that enables systematic comparison and characterization of autonomous agent behavior across trajectories.
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
Q-Evolve unifies automatic process-reward labeling via advantage estimation and behavior-proximal policy optimization inside an in-distribution RL loop to enable self-evolving LLM agents on interactive tasks.
ToolGraph plus DPO on divergence-point preferences lifts weighted average reward on 375 tau2-bench tasks from 0.304 to 0.355.
citing papers explorer
-
CurateEvo: Data-Curation Evolving for Agentic Post-Training
CurateEvo evolves executable data-curation code using failed agent trajectories, improving post-training performance by 3.2 and 2.7 points over baselines on labeled and wild data respectively.
-
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Evoflux applies evolutionary search at inference time to repair executable tool workflows for compact agents, outperforming SFT and SFT+DPO on held-out MCP-Bench tasks with live servers and 250 tools.
-
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
COMAP co-evolves textual world models and agent policies for LLMs through on-policy self-distillation, yielding up to 16.75% relative gains on embodied planning, web navigation, and tool-use tasks.
-
How to Interpret Agent Behavior
ACT*ONOMY is a Grounded-Theory-derived hierarchical taxonomy and open repository that enables systematic comparison and characterization of autonomous agent behavior across trajectories.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
-
Self-evolving LLM agents with in-distribution Optimization
Q-Evolve unifies automatic process-reward labeling via advantage estimation and behavior-proximal policy optimization inside an in-distribution RL loop to enable self-evolving LLM agents on interactive tasks.
-
Self-Evolution for Multi-Turn Tool-Calling Agents via Divergence-Point Preference Learning
ToolGraph plus DPO on divergence-point preferences lifts weighted average reward on 375 tau2-bench tasks from 0.304 to 0.355.