Self-GC governs agent context as indexed objects with planner-proposed actions, achieving 84.85% no-impact on future continuations on a hard set versus 54-70% for baselines.
arXiv preprint arXiv:2601.06007 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
Goal clarifications lose nearly all value after 10% of execution while input clarifications retain value until roughly 50%, and asking any type past mid-trajectory hurts performance more than never asking.
Cheaper LLM judges match frontier models on citation-quality F1 but differ substantially in false positive and false negative rates, meaning reward signal calibration matters more than model cost.
RAH improves coding performance on Oolong-Synthetic from 71.75% to 81.36% with fixed GPT-5 backbone by spawning subagent harnesses via executable scripts.
Empirical evaluation of eight memory condensation strategies on 480 DiscoveryBench tasks finds no significant impact on hypothesis quality but domain-dependent differences in token efficiency.
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.
citing papers explorer
-
Self-GC: Self-Governing Context for Long-Horizon LLM Agents
Self-GC governs agent context as indexed objects with planner-proposed actions, achieving 84.85% no-impact on future continuations on a hard set versus 54-70% for baselines.
-
Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
Goal clarifications lose nearly all value after 10% of execution while input clarifications retain value until roughly 50%, and asking any type past mid-trajectory hurts performance more than never asking.
-
Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution
Cheaper LLM judges match frontier models on citation-quality F1 but differ substantially in false positive and false negative rates, meaning reward signal calibration matters more than model cost.
-
Recursive Agent Harnesses
RAH improves coding performance on Oolong-Synthetic from 71.75% to 81.36% with fixed GPT-5 backbone by spawning subagent harnesses via executable scripts.
-
Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery
Empirical evaluation of eight memory condensation strategies on 480 DiscoveryBench tasks finds no significant impact on hypothesis quality but domain-dependent differences in token efficiency.
-
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
The Workload-Router-Pool architecture is a 3D framework for LLM inference optimization that synthesizes prior vLLM work into a 3x3 interaction matrix and proposes 21 research directions at the intersections.