SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
arXiv preprint arXiv:2510.21618 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
dataset 1
citation-polarity summary
years
2026 11representative citing papers
TACO combines Differential Answer-Probe Reward (DAPR) and Outcome-Gated Advantage Routing (OGAR) to assign credit to tool calls in agentic visual reasoning, producing accuracy gains on multimodal benchmarks.
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.
Agents that evolve pseudo-tool search descriptions during execution reach an 84.3% StableToolBench pass rate, +26.7 points over static query retrieval, with gains growing with base-model capability.
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
EvoSOP enables LLM agents to self-evolve by iteratively synthesizing atomic tool actions into reusable Standard Operating Procedures, improving success rates and reducing reasoning rounds on ACEBench and Tau2Bench.
APPO improves LLM agent training by branching at tokens selected for both uncertainty and future impact, then scaling credit for consequential reasoning procedures.
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.
RoboAgent chains basic vision-language capabilities inside a single VLM via a scheduler and trains it in three stages (behavior cloning, DAgger, RL) to improve embodied task planning.
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.
LLM agent memory is organized into Storage (preserving trajectories), Reflection (refining them), and Experience (abstracting into reusable knowledge) stages driven by needs for long-range consistency, dynamic adaptation, and continual learning.
citing papers explorer
-
SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
-
TACO: Tool-Augmented Credit Optimization for Agentic Tool Use
TACO combines Differential Answer-Probe Reward (DAPR) and Outcome-Gated Advantage Routing (OGAR) to assign credit to tool calls in agentic visual reasoning, producing accuracy gains on multimodal benchmarks.
-
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.
-
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval
Agents that evolve pseudo-tool search descriptions during execution reach an 84.3% StableToolBench pass rate, +26.7 points over static query retrieval, with gains growing with base-model capability.
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
-
From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
EvoSOP enables LLM agents to self-evolve by iteratively synthesizing atomic tool actions into reusable Standard Operating Procedures, improving success rates and reducing reasoning rounds on ACEBench and Tau2Bench.
-
APPO: Agentic Procedural Policy Optimization
APPO improves LLM agent training by branching at tokens selected for both uncertainty and future impact, then scaling credit for consequential reasoning procedures.
-
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.
-
RoboAgent: Chaining Basic Capabilities for Embodied Task Planning
RoboAgent chains basic vision-language capabilities inside a single VLM via a scheduler and trains it in three stages (behavior cloning, DAgger, RL) to improve embodied task planning.
-
Large Databases Need Small, Open-Weight Language Models
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.
-
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
LLM agent memory is organized into Storage (preserving trajectories), Reflection (refining them), and Experience (abstracting into reusable knowledge) stages driven by needs for long-range consistency, dynamic adaptation, and continual learning.