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.
Adaptation of agentic AI: A survey of post-training, memory, and skills
13 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
13
Pith papers citing it
1
external citations · external index
citation-role summary
background 2
citation-polarity summary
years
2026 13roles
background 2polarities
background 2representative citing papers
IdleSpec improves LLM agent accuracy by generating and aggregating speculative plans during idle time between tool calls and observations using complementary drafting strategies.
LLM self-reports predict behavior selectively: TPB reaches human-level coherence within shared conversations but collapses across sessions for primed behaviors, unlike Big 5, with persona prompting stabilizing reports but not actions.
ExpGraph builds a graph of summarized agent experiences and uses graph diffusion plus an RL-trained retrieval copilot to improve frozen LLM executors on QA, math, code, and agentic tasks without parameter updates.
Scaling the delegation backbone in hierarchical search agents improves EM by ~11 points while scaling the executor moves EM by only ~2.6 points, and a 1.7B SFT executor matches a frontier sub-agent at 37% fewer tokens.
Trace2Policy's EISR iteratively refines expert-derived rules into compiled Python code reaching 79.6% accuracy on skewed compliance tasks, outperforming one-shot LLM distillation and a deployed LLM baseline.
Ace-Skill boosts multimodal agent self-evolution via prioritized rollouts with lazy-decay tracking and semantic knowledge clustering, yielding up to 35% relative gains on tool-use benchmarks and zero-shot transfer to smaller models.
NSI lifts interaction traces into logic programs to enable few-shot skill induction and adaptation for long-horizon agentic tasks.
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
M-ArtAgent applies a falsification-governed multimodal agent with StyleComparator and ConceptRetriever operators to implicit art influence discovery and reports 83.7% F1 on the WIB-100 benchmark.
Distinguishes agentic (externally scaffolded) from agentive (internally structured) AI systems and proposes the Goal-Identity-Configurator architecture for endogenous autonomy.
Agent Cybernetics reframes foundation agent design by adapting classical cybernetics laws into three engineering desiderata for reliable, long-running, self-improving agents.
citing papers explorer
-
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.
-
IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents
IdleSpec improves LLM agent accuracy by generating and aggregating speculative plans during idle time between tool calls and observations using complementary drafting strategies.
-
Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior
LLM self-reports predict behavior selectively: TPB reaches human-level coherence within shared conversations but collapses across sessions for primed behaviors, unlike Big 5, with persona prompting stabilizing reports but not actions.
-
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents
ExpGraph builds a graph of summarized agent experiences and uses graph diffusion plus an RL-trained retrieval copilot to improve frozen LLM executors on QA, math, code, and agentic tasks without parameter updates.
-
Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?
Scaling the delegation backbone in hierarchical search agents improves EM by ~11 points while scaling the executor moves EM by only ~2.6 points, and a 1.7B SFT executor matches a frontier sub-agent at 37% fewer tokens.
-
Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
Trace2Policy's EISR iteratively refines expert-derived rules into compiled Python code reaching 79.6% accuracy on skewed compliance tasks, outperforming one-shot LLM distillation and a deployed LLM baseline.
-
Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution
Ace-Skill boosts multimodal agent self-evolution via prioritized rollouts with lazy-decay tracking and semantic knowledge clustering, yielding up to 35% relative gains on tool-use benchmarks and zero-shot transfer to smaller models.
-
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
NSI lifts interaction traces into logic programs to enable few-shot skill induction and adaptation for long-horizon agentic tasks.
-
Heterogeneous Scientific Foundation Model Collaboration
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
-
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
-
M-ArtAgent: Evidence-Based Multimodal Agent for Implicit Art Influence Discovery
M-ArtAgent applies a falsification-governed multimodal agent with StyleComparator and ConceptRetriever operators to implicit art influence discovery and reports 83.7% F1 on the WIB-100 benchmark.
-
Critique of Agent Model
Distinguishes agentic (externally scaffolded) from agentive (internally structured) AI systems and proposes the Goal-Identity-Configurator architecture for endogenous autonomy.
-
The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
Agent Cybernetics reframes foundation agent design by adapting classical cybernetics laws into three engineering desiderata for reliable, long-running, self-improving agents.