SkillComposer performs task-conditioned skill sequence prediction with a constrained autoregressive decoder to jointly output skill subset, count, and order, raising pass rates by 23.1 and 18.2 percentage points on two production coding agents over no-skill baselines.
International Conference on Learning Representations , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Survey of 112 agentic AI for social good papers reveals moral-geographic asymmetry with 73% lacking geographic context (lowest for SDG 16) and only 25% reporting deployments.
Proposes a three-step benchmark design method (define work activity, specify tested setting, score work product) derived from work studies and O*NET, demonstrated via three case analyses.
Introduces predictive prefetching for RAG that anticipates retrieval needs several tokens ahead via three components, reporting up to 43.5% latency reduction and 62.4% TTFT improvement while preserving answer quality.
Parallel WebBench reveals GRPO training raises web agent completion to 96% but leaves a large correctness gap from context-bound loops, premature termination, and synthesis collapse.
This survey defines execution provenance as a typed graph of agent execution and evidence tracing as its projection onto evidence-support relations, then reviews methods, taxonomy, benchmarks, and challenges for auditable LLM agents.
A role-based multi-agent architecture with four hierarchical layers is introduced to bridge business support systems and operations support systems for intent-driven network orchestration.
citing papers explorer
-
Generative Skill Composition for LLM Agents
SkillComposer performs task-conditioned skill sequence prediction with a constrained autoregressive decoder to jointly output skill subset, count, and order, raising pass rates by 23.1 and 18.2 percentage points on two production coding agents over no-skill baselines.
-
Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good
Survey of 112 agentic AI for social good papers reveals moral-geographic asymmetry with 73% lacking geographic context (lowest for SDG 16) and only 25% reporting deployments.
-
Design and Report Benchmarks for Knowledge Work
Proposes a three-step benchmark design method (define work activity, specify tested setting, score work product) derived from work studies and O*NET, demonstrated via three case analyses.
-
Predictive Prefetching for Retrieval-Augmented Generation
Introduces predictive prefetching for RAG that anticipates retrieval needs several tokens ahead via three components, reporting up to 43.5% latency reduction and 62.4% TTFT improvement while preserving answer quality.
-
When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration
Parallel WebBench reveals GRPO training raises web agent completion to 96% but leaves a large correctness gap from context-bound loops, premature termination, and synthesis collapse.
-
From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
This survey defines execution provenance as a typed graph of agent execution and evidence tracing as its projection onto evidence-support relations, then reviews methods, taxonomy, benchmarks, and challenges for auditable LLM agents.
-
Role-Based Agentic AI for Intent-Driven Network and Service Orchestration
A role-based multi-agent architecture with four hierarchical layers is introduced to bridge business support systems and operations support systems for intent-driven network orchestration.