MASPrism attributes failures in multi-agent systems by ranking candidates from prefill-stage NLL and attention signals of a 0.6B SLM, beating baselines by up to 33.41% Top-1 accuracy and proprietary LLMs by up to 89.5% relative improvement while processing traces in 2.66 seconds.
fewer than three fragments
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
verdicts
UNVERDICTED 9polarities
background 3representative citing papers
A new benchmark for 0-to-1 CLI tool generation shows state-of-the-art LLMs achieve under 43% success rate with black-box equivalence testing against real oracles.
GBQA benchmark shows the best frontier LLM finds only 48.39% of verified game bugs using a multi-round ReAct agent with memory.
PRISM detects and stops credential leakage during LLM generation in multi-agent pipelines using per-token risk scores from lexical, structural, and behavioral signals, achieving zero observed leaks and F1 of 0.832 on a 2000-task benchmark.
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.
AiScientist improves ML research benchmarks by 10.54 points on PaperBench and reaches 81.82% Any Medal on MLE-Bench Lite through hierarchical control plus durable file-based state instead of conversational handoffs.
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
EvoDev introduces an iterative feature-driven framework with a DAG-based Feature Map for context propagation that improves LLM agent performance on end-to-end software development tasks by 56.8% over the best baseline.
ErrorProbe introduces a self-improving pipeline for attributing semantic failures in LLM multi-agent systems to specific agents and steps via anomaly detection, backward tracing, and tool-grounded validation with verified episodic memory.
citing papers explorer
-
MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals
MASPrism attributes failures in multi-agent systems by ranking candidates from prefill-stage NLL and attention signals of a 0.6B SLM, beating baselines by up to 33.41% Top-1 accuracy and proprietary LLMs by up to 89.5% relative improvement while processing traces in 2.66 seconds.
-
Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios
A new benchmark for 0-to-1 CLI tool generation shows state-of-the-art LLMs achieve under 43% success rate with black-box equivalence testing against real oracles.
-
GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers
GBQA benchmark shows the best frontier LLM finds only 48.39% of verified game bugs using a multi-round ReAct agent with memory.
-
PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM Pipelines
PRISM detects and stops credential leakage during LLM generation in multi-agent pipelines using per-token risk scores from lexical, structural, and behavioral signals, achieving zero observed leaks and F1 of 0.832 on a 2000-task benchmark.
-
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.
-
Toward Autonomous Long-Horizon Engineering for ML Research
AiScientist improves ML research benchmarks by 10.54 points on PaperBench and reaches 81.82% Any Medal on MLE-Bench Lite through hierarchical control plus durable file-based state instead of conversational handoffs.
-
TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
-
EvoDev: An Iterative Feature-Driven Framework for End-to-End Software Development with LLM-based Agents
EvoDev introduces an iterative feature-driven framework with a DAG-based Feature Map for context propagation that improves LLM agent performance on end-to-end software development tasks by 56.8% over the best baseline.
-
Towards Self-Improving Error Diagnosis in Multi-Agent Systems
ErrorProbe introduces a self-improving pipeline for attributing semantic failures in LLM multi-agent systems to specific agents and steps via anomaly detection, backward tracing, and tool-grounded validation with verified episodic memory.