Claims Browser

Deploying robots to real-world applications requires a long development timeline

"Getting robots to real deployment takes a long time"

Errors accumulate without effective correction in MLLM agents during extended urban exploration

"errors accumulate without effective correction"

MLLM agents' local abilities do not compose into sustained goal-directed behavior over extended exploration

"Their central failure emerges over extended exploration, where local abilities do not compose into sustained goal-directed behavior and errors accumulate without effective correction"

CritICL consistently outperforms standard in-context learning and achieves performance competitive with or superior to test-time scaling methods while requiring significantly fewer generations and lower token cost

"Experimental results show that CritICL consistently outperforms standard in-context learning and achieves performance competitive with or superior to test-time scaling methods, while requiring significantly fewer generations and lower token cost"

CritICL improves reasoning while maintaining high efficiency by leveraging failure modes from weaker models as guidance through critique-based in-context examples

"CritICL, a novel inference-time framework that improves reasoning while maintaining high efficiency. Our key insight is that LLM failure modes exhibit structured patterns across model scales within the same family. Instead of treating failures as undesirable outputs, CritICL leverages them as a source of guidance. Specifically, we utilize failure modes derived from weaker models and incorporate them into inference through critique-based in-context examples"

LLM failure modes exhibit structured patterns across model scales within the same family

"LLM failure modes exhibit structured patterns across model scales within the same family"

Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models

"Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs)"

Agent skills package specialized knowledge and workflows into reusable resources that enable progressive adaptation through interaction

"Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities"

Skill evolution complements model scaling as an approach to improving agent capabilities

"skill evolution complements model scaling"

Persistent knowledge accumulation in the wiki is critical for effective skill evolution

"persistent knowledge accumulation in the wiki is critical for effective skill evolution"

Evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills

"evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills"

Larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them

"larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them"

There are now 38 identifiable patterns of clichéd language produced by LLMs

"My LLM cliché highlighter is up to 38 patterns now"

WikiSkill consistently outperforms state-of-the-art skill-evolution methods across diverse benchmarks and models

"Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods"

Rollouts that disagree with pseudo-labels are typically wrong regardless of whether the vote itself is correct

"rollouts that disagree with the pseudo-label are typically wrong regardless of whether the vote itself is correct"

Majority-vote pseudo-labels are fragile because an incorrect vote corrupts the teacher and misleads every token

"Replacing ground truth with majority-vote pseudo-labels is a natural alternative, yet it is fragile: an incorrect vote corrupts the teacher and misleads every token"

TTPO shows strong cross-task generalization capabilities

"shows strong cross-task generalization"

TTPO yields +25.2% to +36.4% improvement without thinking

"yields +25.2% to +36.4% without thinking"