ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.
hub Canonical reference
arXiv preprint arXiv:2510.23595 , year=
Canonical reference. 75% of citing Pith papers cite this work as background.
17
Pith papers citing it
Background
75% of classified citations
hub tools
citation-role summary
background 6
baseline 1
method 1
citation-polarity summary
years
2026 17representative citing papers
ElasticMem enables LLM agents to learn adaptive latent memory retrieval and elastic budget allocation, improving QA accuracy by 24-26% and ALFWorld success by 27-66% over baselines with lower token cost.
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
EVOCHAMBER enables test-time co-evolution of multi-agent systems across three scales, producing emergent niche specialists and performance gains of up to 32% relative on math tasks with Qwen3-8B.
MAGE uses a four-subgraph co-evolutionary knowledge graph plus dual bandits to externalize and retrieve experience for stable self-evolution of frozen language-model agents, showing gains on nine diverse benchmarks.
EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
An economy of agents using auctions and wealth accumulation produces emergent multi-step reasoning that outperforms monolithic baselines on five agentic tasks.
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
JigsawRL achieves up to 1.85x higher throughput in LLM RL pipelines via pipeline multiplexing, sub-stage graphs, and look-ahead scheduling compared to prior systems.
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.
RQGM enables co-evolution of agents and evaluators across epochs with non-stationary utilities, reporting gains in coding pass rates, paper acceptance, and proof grading over prior self-improving agents.
AI agents in supply chain simulations outperform humans but exhibit decision instability that GRPO post-training reduces.
Randomly masking a proposer's output vocabulary during training and generation sustains curriculum diversity and improves solver accuracy by +4.4 points at 8B in LLM co-evolution.
Agentic AI systems with DAG topologies are claimed to deliver exponentially superior generalization and sample efficiency compared to monolithic scaling for achieving AGI.
This survey organizes RL for LLM multi-agent systems into reward families, credit units, and five orchestration sub-decisions, notes the absence of explicit stopping-decision training in its paper pool, and releases a tagged corpus.
Position paper identifies structural challenges in applying generic agentic AI to Earth Observation and outlines design principles for EO-native agents focused on geospatial state and validity.
citing papers explorer
-
ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments
ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.
-
ElasticMem: Latent Memory as a Learnable Resource for LLM Agents
ElasticMem enables LLM agents to learn adaptive latent memory retrieval and elastic budget allocation, improving QA accuracy by 24-26% and ALFWorld success by 27-66% over baselines with lower token cost.
-
EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
-
EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
EVOCHAMBER enables test-time co-evolution of multi-agent systems across three scales, producing emergent niche specialists and performance gains of up to 32% relative on math tasks with Qwen3-8B.
-
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
MAGE uses a four-subgraph co-evolutionary knowledge graph plus dual bandits to externalize and retrieve experience for stable self-evolution of frozen language-model agents, showing gains on nine diverse benchmarks.
-
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.
-
MetaPS: Adaptive Programmatic Strategy Selection for Market Agents
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
-
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
An economy of agents using auctions and wealth accumulation produces emergent multi-step reasoning that outperforms monolithic baselines on five agentic tasks.
-
AIPO: Learning to Reason from Active Interaction
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
-
JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training
JigsawRL achieves up to 1.85x higher throughput in LLM RL pipelines via pipeline multiplexing, sub-stage graphs, and look-ahead scheduling compared to prior systems.
-
Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.
-
The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
RQGM enables co-evolution of agents and evaluators across epochs with non-stationary utilities, reporting gains in coding pass rates, paper acceptance, and proof grading over prior self-improving agents.
-
Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
AI agents in supply chain simulations outperform humans but exhibit decision instability that GRPO post-training reduces.
-
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Randomly masking a proposer's output vocabulary during training and generation sustains curriculum diversity and improves solver accuracy by +4.4 points at 8B in LLM co-evolution.
-
Position: Agentic AI System Is a Foreseeable Pathway to AGI
Agentic AI systems with DAG topologies are claimed to deliver exponentially superior generalization and sample efficiency compared to monolithic scaling for achieving AGI.
-
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
This survey organizes RL for LLM multi-agent systems into reward families, credit units, and five orchestration sub-decisions, notes the absence of explicit stopping-decision training in its paper pool, and releases a tagged corpus.
-
Agentic AI for Remote Sensing: Technical Challenges and Research Directions
Position paper identifies structural challenges in applying generic agentic AI to Earth Observation and outlines design principles for EO-native agents focused on geospatial state and validity.