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.
Agent-r: Train- ing language model agents to reflect via iterative self-training
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 9roles
background 1polarities
background 1representative citing papers
SEAL co-evolves LLM agents and environments via shared turn-level failure diagnoses, yielding +8.25 to +26.25 point gains on tool-use tasks with only 400 samples.
Skill-SD turns an agent's completed trajectories into dynamic natural-language skills that condition only the teacher in self-distillation, yielding 14-42% gains over RL and OPSD baselines on multi-turn agent benchmarks.
TEC is a new public dataset of detailed human trial-and-error trajectories and reflections on web tasks, with humans showing substantially higher accuracy than LLMs.
MEM1 uses end-to-end RL to learn constant-memory agents that update a shared state for memory and reasoning, delivering 3.5x better performance and 3.7x lower memory use than larger baselines on long-horizon QA and shopping tasks.
A constrained verifiable agent framework for open-web data collection achieves zero execution-stage LLM tokens and lowest wall-clock time on 80 verified tasks by shifting from free-form code to typed JSON configs with taxonomy and static DAG execution.
RoboAgent chains basic vision-language capabilities inside a single VLM via a scheduler and trains it in three stages (behavior cloning, DAgger, RL) to improve embodied task planning.
An automated environment construction pipeline plus verifiable rewards enables RL training that improves LLM tool-use performance across scales without harming general capabilities.
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.
citing papers explorer
-
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.
-
Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection
A constrained verifiable agent framework for open-web data collection achieves zero execution-stage LLM tokens and lowest wall-clock time on 80 verified tasks by shifting from free-form code to typed JSON configs with taxonomy and static DAG execution.
-
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.