Object Aligner provides a schema-configurable deterministic similarity metric for JSON objects and graphs using tree alignment and Weisfeiler-Leman referential alignment, applied as a reward in LLM prompt optimization.
hub
falling piece
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
HALO trains an orchestrator policy on verifier-approved refinement trajectories across 11 PDDL domains, matching GPT-5-mini success rates at roughly 45x lower orchestration cost and cutting LLM calls by 40-50%.
TransitLM is a large-scale dataset and benchmark for training LLMs to generate structurally valid map-free transit routes from origin-destination pairs.
IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
Reasoning Primitive Induction mines ReAct traces to build a library of typed pseudo-tools that, when composed in a standard ReAct loop, outperform the original agent by 22-44 percentage points on five subtasks.
LLM planning in four-in-a-row is myopic: move choices match a shallow model that ignores deep nodes expanded in reasoning traces.
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
Dream 7B is a 7B diffusion LLM that refines sequences in parallel via denoising and outperforms prior diffusion models on general, mathematical, and coding benchmarks with added flexibility in generation order and quality-speed tradeoffs.
ChinaTravel is a benchmark with sandbox, compositional DSL, and 1154-human dataset for testing language agents on open-ended travel planning constraint satisfaction.
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
Einstein World Models integrate visual rollouts from a callable world-module into LLM reasoning traces to support complex thought beyond language.
An end-to-end LLM framework refines natural language into valid PDDL domains and problems via hardcoded and dynamic agents, generates plans with standard engines, and returns readable output.
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
citing papers explorer
-
Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization
Object Aligner provides a schema-configurable deterministic similarity metric for JSON objects and graphs using tree alignment and Weisfeiler-Leman referential alignment, applied as a reward in LLM prompt optimization.
-
Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents
HALO trains an orchestrator policy on verifier-approved refinement trajectories across 11 PDDL domains, matching GPT-5-mini success rates at roughly 45x lower orchestration cost and cutting LLM calls by 40-50%.
-
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
TransitLM is a large-scale dataset and benchmark for training LLMs to generate structurally valid map-free transit routes from origin-destination pairs.
-
IE as Cache: Information Extraction Enhanced Agentic Reasoning
IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
-
A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
Supervised fine-tuning lets LLMs linearly encode action validity and state predicates, with broader state-space coverage during training improving world-model recovery.
-
Inducing Reasoning Primitives from Agent Traces
Reasoning Primitive Induction mines ReAct traces to build a library of typed pseudo-tools that, when composed in a standard ReAct loop, outperform the original agent by 22-44 percentage points on five subtasks.
-
Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
LLM planning in four-in-a-row is myopic: move choices match a shallow model that ignores deep nodes expanded in reasoning traces.
-
DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
-
Dream 7B: Diffusion Large Language Models
Dream 7B is a 7B diffusion LLM that refines sequences in parallel via denoising and outperforms prior diffusion models on general, mathematical, and coding benchmarks with added flexibility in generation order and quality-speed tradeoffs.
-
ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
ChinaTravel is a benchmark with sandbox, compositional DSL, and 1154-human dataset for testing language agents on open-ended travel planning constraint satisfaction.
-
Training Language Models to Self-Correct via Reinforcement Learning
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
-
Einstein World Models
Einstein World Models integrate visual rollouts from a callable world-module into LLM reasoning traces to support complex thought beyond language.
-
End-to-end PDDL Planning with Hardcoded and Dynamic Agents
An end-to-end LLM framework refines natural language into valid PDDL domains and problems via hardcoded and dynamic agents, generates plans with standard engines, and returns readable output.
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
- Learning to Interrupt in Language-based Multi-agent Communication