BSLI is a Bayesian selective inference method that maintains posteriors over latent burden and identifiability, uses scientific gates for answerability, and optimizes cost-calibrated query-stop decisions via an exact Bellman policy, showing improved performance on a large benchmark.
hub Mixed citations
Chawla, Olaf Wiest, and Xiangliang Zhang
Mixed citation behavior. Most common role is background (60%).
20
Pith papers citing it
178
external citations · Crossref
Background
60% of classified citations
hub tools
citation-role summary
background 3
baseline 1
method 1
citation-polarity summary
representative citing papers
A folk theorem for LLM guides: any feasible, individually rational payoff vector can be sustained as an ε-equilibrium despite unobservable, unattributable deviations.
A novel function hijacking attack achieves 70-100% success rates in forcing specific function calls across five LLMs on the BFCL benchmark and is robust to context semantics.
STE is a differentiable method to compute continuous analogues of the Top Cycle and Uncovered Set from pairwise comparison data for stable set-valued evaluation of cyclic agent interactions.
Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Brier-score improvement over random.
A lightweight VLM inspecting SMAC policy videos produces open-ended multi-agent curricula that outperform text-only ablations and PLR scalar-score methods on held-out maps.
Formalizes design space for human-LLM collaborative planning along mode, scope, and level axes; evaluates AMBIPOM prototype via user study and benchmark revealing hybrid workflows and trade-offs.
FuzzAgent deploys specialized agents that collaborate on harness generation, execution, and crash triage to evolve fuzzing campaigns, delivering 45-191% more branch coverage than four baselines on 20 C/C++ libraries and surfacing 102 real bugs.
A tabular foundation model with LLM-as-Observer features predicts AI agent decisions in controlled games, outperforming baselines by 4 AUC points and 14% lower error at K=16 interactions.
A new filtration-based conformal prediction method attributes errors in multi-agent systems by producing contiguous sequence sets with finite-sample coverage guarantees, enabling rollback recovery.
ETI lets LLM agents infer and track partners' psychological traits (warmth and competence) from histories, cutting payoff loss 45-77% in games and boosting performance 3-29% on MultiAgentBench versus CoT baselines.
GBC treats multi-agent LLM workflows as differentiable graphs to enable token-level attribution and targeted optimization, with reported gains on MultiWOZ and τ-bench.
Large-scale experiment with 1440 task executions finds dynamic routing of coordination strategies achieves near-best quality scores across models and classes but does not reliably identify exact winners.
A comprehensive review synthesizing AI-driven sperm analysis across computer vision tasks, multimodal fusion, and a staged clinical translation roadmap.
Metagente is an LLM multi-agent system using Teacher-Student collaboration that outperforms baselines on real-world software documentation summarization for requirements analysis and technical docs.
A hybrid closed-form and greedy algorithm minimizes total energy in wireless MEAN by dynamically switching agents between BS-assisted semantic collaboration and local execution.
On-demand runtime generation of persona-based agents can enable personalized multi-agent AI workflows beyond fixed hard-coded architectures.
Software engineering is undergoing a paradigm shift to AI-native practices centered on agentic systems rather than traditional code.
Introduces a multi-agent AI system for optical power optimization in multi-band links, claiming 689 Tbps traffic gain with 303 average interactions in network evaluations.
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
citing papers explorer
-
Bayesian Selective Latent Inference for Wastewater-First Influenza Monitoring
BSLI is a Bayesian selective inference method that maintains posteriors over latent burden and identifiability, uses scientific gates for answerability, and optimizes cost-calibrated query-stop decisions via an exact Bellman policy, showing improved performance on a large benchmark.
-
Who Is Really Playing? Strategic Interaction in AI-Guided Populations
A folk theorem for LLM guides: any feasible, individually rational payoff vector can be sustained as an ε-equilibrium despite unobservable, unattributable deviations.
-
Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
A novel function hijacking attack achieves 70-100% success rates in forcing specific function calls across five LLMs on the BFCL benchmark and is robust to context semantics.
-
Soft Tournament Equilibrium
STE is a differentiable method to compute continuous analogues of the Top Cycle and Uncovered Set from pairwise comparison data for stable set-valued evaluation of cyclic agent interactions.
-
Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia
Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Brier-score improvement over random.
-
Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs
A lightweight VLM inspecting SMAC policy videos produces open-ended multi-agent curricula that outperform text-only ablations and PLR scalar-score methods on held-out maps.
-
How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
Formalizes design space for human-LLM collaborative planning along mode, scope, and level axes; evaluates AMBIPOM prototype via user study and benchmark revealing hybrid workflows and trade-offs.
-
FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing
FuzzAgent deploys specialized agents that collaborate on harness generation, execution, and crash triage to evolve fuzzing campaigns, delivering 45-191% more branch coverage than four baselines on 20 C/C++ libraries and surfacing 102 real bugs.
-
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
A tabular foundation model with LLM-as-Observer features predicts AI agent decisions in controlled games, outperforming baselines by 4 AUC points and 14% lower error at K=16 interactions.
-
Conformal Agent Error Attribution
A new filtration-based conformal prediction method attributes errors in multi-agent systems by producing contiguous sequence sets with finite-sample coverage guarantees, enabling rollback recovery.
-
Explicit Trait Inference for Multi-Agent Coordination
ETI lets LLM agents infer and track partners' psychological traits (warmth and competence) from histories, cutting payoff loss 45-77% in games and boosting performance 3-29% on MultiAgentBench versus CoT baselines.
-
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
GBC treats multi-agent LLM workflows as differentiable graphs to enable token-level attribution and targeted optimization, with reported gains on MultiWOZ and τ-bench.
-
Dynamic Coordination Strategy Selection for Enterprise Multi-Agent Systems
Large-scale experiment with 1440 task executions finds dynamic routing of coordination strategies achieves near-best quality scores across models and classes but does not reliably identify exact winners.
-
Deep Learning for Semen Analysis in Male Infertility: Computer Vision, Multimodal Fusion, and Clinical Translation
A comprehensive review synthesizing AI-driven sperm analysis across computer vision tasks, multimodal fusion, and a staged clinical translation roadmap.
-
Automated Summarization of Software Documents: An LLM-based Multi-Agent Approach
Metagente is an LLM multi-agent system using Teacher-Student collaboration that outperforms baselines on real-world software documentation summarization for requirements analysis and technical docs.
-
Joint Communication and Computation Design for Mobile Embodied AI Network (MEAN)
A hybrid closed-form and greedy algorithm minimizes total energy in wireless MEAN by dynamically switching agents between BS-assisted semantic collaboration and local execution.
-
Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needs
On-demand runtime generation of persona-based agents can enable personalized multi-agent AI workflows beyond fixed hard-coded architectures.
-
From Determinism to Delegation: AI-Native Software Engineering and the Evolution of the Agentic Engineer
Software engineering is undergoing a paradigm shift to AI-native practices centered on agentic systems rather than traditional code.
-
Efficient Multi-Agent Optimization of Optical Power in S+C+L-Band Systems
Introduces a multi-agent AI system for optical power optimization in multi-band links, claiming 689 Tbps traffic gain with 303 average interactions in network evaluations.
-
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.