Event-graph substrates represent states as RDF triple logs, prove a duality reducing explanatory and counterfactual queries to causal-ancestor traversal, and outperform symbolic and parametric baselines on CLEVRER and a new Smallville benchmark.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 10roles
method 1polarities
use method 1representative citing papers
OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.
Introduces MPT benchmark and PRefine method that models user preferences as evolving hypotheses to improve personalized tool calling accuracy with 1.24% of full-history token cost.
Weasel is a trajectory selection method that improves out-of-domain generalization for web agents while achieving 9.7-12.5x training speedups via importance-diversity optimization, AXTree pruning, and rationale style matching.
A dual hierarchical RL framework with two agents coordinates high-level dialogue strategy and low-level question generation to emulate judicial questioning and extract key information from Supreme Court arguments, outperforming baselines.
MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.
EvoSOP enables LLM agents to self-evolve by iteratively synthesizing atomic tool actions into reusable Standard Operating Procedures, improving success rates and reducing reasoning rounds on ACEBench and Tau2Bench.
Proposes skill distillation from user browser trajectories into a graph of natural-language skills for scalable behavior cloning in browser agents.
SABA improves LLM performance on detective puzzle benchmarks by recursively fusing information into a base state and using queries to resolve missing premises before concluding.
Workplace agent success on WorkBench rose from 43% to 98% over two years with sharply reduced harmful actions.
citing papers explorer
-
Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning
Event-graph substrates represent states as RDF triple logs, prove a duality reducing explanatory and counterfactual queries to causal-ancestor traversal, and outperform symbolic and parametric baselines on CLEVRER and a new Smallville benchmark.
-
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
OLIVIA treats LLM agent action selection as a contextual linear bandit over frozen hidden states and applies UCB exploration to adapt online, yielding consistent gains over static ReAct and prompt-based baselines on four benchmarks.
-
Latent Preference Modeling for Cross-Session Personalized Tool Calling
Introduces MPT benchmark and PRefine method that models user preferences as evolving hypotheses to improve personalized tool calling accuracy with 1.24% of full-history token cost.
-
Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection
Weasel is a trajectory selection method that improves out-of-domain generalization for web agents while achieving 9.7-12.5x training speedups via importance-diversity optimization, AXTree pruning, and rationale style matching.
-
Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents
A dual hierarchical RL framework with two agents coordinates high-level dialogue strategy and low-level question generation to emulate judicial questioning and extract key information from Supreme Court arguments, outperforming baselines.
-
MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service
MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.
-
From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
EvoSOP enables LLM agents to self-evolve by iteratively synthesizing atomic tool actions into reusable Standard Operating Procedures, improving success rates and reducing reasoning rounds on ACEBench and Tau2Bench.
-
Scalable Behaviour Cloning on Browser Using via Skill Distillation
Proposes skill distillation from user browser trajectories into a graph of natural-language skills for scalable behavior cloning in browser agents.
-
Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness
SABA improves LLM performance on detective puzzle benchmarks by recursively fusing information into a base state and using queries to resolve missing premises before concluding.
-
WorkBench Revisited: Workplace Agents Two Years On
Workplace agent success on WorkBench rose from 43% to 98% over two years with sharply reduced harmful actions.