Related papers: CAPE: Capability Achievement via Policy Execution
Extracting commonsense knowledge from a large language model (LLM) offers a path to designing intelligent robots. Existing approaches that leverage LLMs for planning are unable to recover when an action fails and often resort to retrying…
Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they remain vulnerable in environments where a single error often leads to irrecoverable…
Automated Feature Engineering (AFE) refers to automatically generate and select optimal feature sets for downstream tasks, which has achieved great success in real-world applications. Current AFE methods mainly focus on improving the…
While frontier formal mathematics systems now routinely develop repository-scale proof engineering artifacts requiring multi-file coordination and semantic correctness beyond compilation, existing evaluation benchmarks remain focused on…
Temporal planning offers numerous advantages when based on an expressive representation. Timelines have been known to provide the required expressiveness but at the cost of search efficiency. We propose here a temporal planner, called FAPE,…
Pre-Requirement Specification traceability is the activity of capturing relations between requirements and their sources, in particular user needs. Requirements are formal technical specifications in the solution space; needs are natural…
As artificial intelligence (AI) systems evolve from stateless chatbots to autonomous multi-step agents, prompt engineering (PE), the discipline of crafting individual queries, proves necessary but insufficient. This paper introduces context…
Tackling large approximate dynamic programming or reinforcement learning problems requires methods that can exploit regularities, or intrinsic structure, of the problem in hand. Most current methods are geared towards exploiting the…
We introduce a new preference-based framework for conditional treatment effect estimation and policy learning, built on the Conditional Preference-based Treatment Effect (CPTE). CPTE requires only that outcomes be ranked under a preference…
This paper details the methodology behind CoPE, a policy-steerable small language model capable of fast and accurate content labeling. We present a novel training curricula called Contradictory Example Training that enables the model to…
Satisfactory software performance is essential for the adoption and the success of a product. In organizations that follow traditional software development models (e.g., waterfall), Software Performance Engineering (SPE) involves…
While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many requirements must be tracked across grounding, generation, and verification. We refer to…
When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We…
Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs. While methods like Direct Preference Optimization (DPO) have…
Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such…
Programming by example (PBE) is an emerging programming paradigm that automatically synthesizes programs specified by user-provided input-output examples. Despite the convenience for end-users, implementing PBE tools often requires strong…
Runtime uncertainty such as unpredictable resource unavailability, changing environmental conditions and user needs, as well as system intrusions or faults represents one of the main current challenges of self-adaptive systems. Moreover,…
Human expectations arise from their understanding of others and the world. In the context of human-AI interaction, this understanding may not align with reality, leading to the AI agent failing to meet expectations and compromising team…
Current evaluation frameworks for foundation models rely heavily on static, manually curated benchmarks, limiting their ability to capture the full breadth of model capabilities. This paper introduces Active learning for Capability…
Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for simple problems. We present Length-Adaptive Policy…