Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
hub
Flex: Continuous agent evolution via forward learning from experience
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 3
dataset 1
citation-polarity summary
polarities
background 4representative citing papers
EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.
Evolving-RL jointly optimizes experience extraction and utilization in LLM agents via RL with separate evaluation signals, delivering up to 98.7% relative gains on out-of-distribution tasks in ALFWorld and Mind2Web.
HC-INR uses a hierarchical hypernetwork to warp input coordinates into a disentangled space, raising the representable frequency bound while cutting parameters by 30-60% and boosting fidelity up to 4x over prior INRs.
NSTR models space-varying frequency fields in implicit neural representations by learning a frequency transport PDE that modulates global sinusoids, achieving better accuracy-parameter trade-offs than SIREN or Instant-NGP on images, audio, and 3D tasks.
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.
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
Mem-π is a framework using a dedicated model and decision-content decoupled RL to generate context-specific guidance on demand for LLM agents, outperforming retrieval baselines by over 30% on web navigation.
CASCADE enables LLMs to continually adapt at deployment via case-based episodic memory and contextual bandits, improving macro-averaged success by 20.9% over zero-shot on 16 tasks spanning medicine, law, code, and robotics.
GenericAgent outperforms other LLM agents on long-horizon tasks by maximizing context information density with fewer tokens via minimal tools, on-demand memory, trajectory-to-SOP evolution, and compression.
Reflective evolution of executable Python memory programs finds task-specific Schema/Logic/Instruction designs that beat fixed memory baselines across conversation, embodied, medical, and professional reasoning tasks.
MILES dynamically expands step-wise memory with learnable selection heads that rerank candidates and guide reasoning, improving LLM test-time performance under limited supervision.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
EvoIR-Agent introduces a hierarchical experience pool and self-evolving mechanism to improve training-free image restoration agents, claiming significant metric leads and better performance-efficiency balance.
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.
citing papers explorer
-
Co-Evolving Skill Generation and Policy Optimization
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
-
EXG: Self-Evolving Agents with Experience Graphs
EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.
-
Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
Evolving-RL jointly optimizes experience extraction and utilization in LLM agents via RL with separate evaluation signals, delivering up to 98.7% relative gains on out-of-distribution tasks in ALFWorld and Mind2Web.
-
Scaling Implicit Fields via Hypernetwork-Driven Multiscale Coordinate Transformations
HC-INR uses a hierarchical hypernetwork to warp input coordinates into a disentangled space, raising the representable frequency bound while cutting parameters by 30-60% and boosting fidelity up to 4x over prior INRs.
-
NSTR: Neural Spectral Transport Representation for Space-Varying Frequency Fields
NSTR models space-varying frequency fields in implicit neural representations by learning a frequency transport PDE that modulates global sinusoids, achieving better accuracy-parameter trade-offs than SIREN or Instant-NGP on images, audio, and 3D tasks.
-
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.
-
Rethinking Memory as Continuously Evolving Connectivity
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
-
Mem-$\pi$: Adaptive Memory through Learning When and What to Generate
Mem-π is a framework using a dedicated model and decision-content decoupled RL to generate context-specific guidance on demand for LLM agents, outperforming retrieval baselines by over 30% on web navigation.
-
CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
CASCADE enables LLMs to continually adapt at deployment via case-based episodic memory and contextual bandits, improving macro-averaged success by 20.9% over zero-shot on 16 tasks spanning medicine, law, code, and robotics.
-
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
GenericAgent outperforms other LLM agents on long-horizon tasks by maximizing context information density with fewer tokens via minimal tools, on-demand memory, trajectory-to-SOP evolution, and compression.
-
M$^\star$: Every Task Deserves Its Own Memory Harness
Reflective evolution of executable Python memory programs finds task-specific Schema/Logic/Instruction designs that beat fixed memory baselines across conversation, embodied, medical, and professional reasoning tasks.
-
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
MILES dynamically expands step-wise memory with learnable selection heads that rerank candidates and guide reasoning, improving LLM test-time performance under limited supervision.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning
EvoIR-Agent introduces a hierarchical experience pool and self-evolving mechanism to improve training-free image restoration agents, claiming significant metric leads and better performance-efficiency balance.
-
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
-
Context Training with Active Information Seeking
Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.