A new native-runtime benchmark reveals that current frontier AI agents succeed on at most 62 percent of realistic long-horizon CLI tasks.
React: Synergizing reasoning and acting in language models
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 9representative citing papers
MiCP is the first conformal prediction method for multi-turn LLM pipelines that allocates per-turn error budgets to enable adaptive stopping with an overall coverage guarantee, shown to reduce turns and cost on RAG and ReAct benchmarks.
DOLORES, an agent using a formal language for meta-reasoning to construct adaptive scaffolds on the fly, outperforms prior scaffolding methods by 24.8% on average across four hard benchmarks and multiple model sizes.
FitText embeds evolutionary retrieval of tool descriptions into the agent loop, yielding 2.7-10.6 point NDCG@5 gains on ToolRet and 26.7-point pass-rate gains on StableToolBench.
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.
ExecTune trains guide models via acceptance sampling, supervised fine-tuning, and structure-aware RL to boost executability of strategies for black-box LLMs, yielding up to 9.2% higher accuracy and 22.4% lower cost on math and code tasks.
An LLM agent autonomously selects, codes, and validates materials equations from data, recovering known laws reliably but requiring checks for new or specialized cases.
Thinking with Drafting reconceptualizes visual reasoning as optical decompression by forcing models to draft mental models into executable DSL code for deterministic self-verification on the VisAlg benchmark.