Human Feedback and Eval Paper Explorer

Match reason: Matches selected tags (Demonstrations).

• Current approaches either rely on prompting to elicit the model's innate agent capabilities, or suffer from performance ceilings and collapse when applying RL to complex interactive tasks, leaving their true agentic potential untapped.
• To address this, we introduce Dynamic-filter Sequence-level Policy Optimization (DSPO), an improved RL algorithm designed for robust agent training through sequence-level optimization and dynamic sample filtering.

Match reason: Matches selected tags (Demonstrations).

• Across seven mathematical benchmarks, LightReasoner improves accuracy by up to 28.1%, while reducing time consumption by 90%, sampled problems by 80%, and tuned token usage by 99%, all without relying on ground-truth labels.

Match reason: Matches selected tags (Demonstrations).

• Computer-using agents (CUAs) must plan task workflows across diverse and evolving applications, yet progress is limited by the lack of large-scale, high-quality training data.
• We present Watch & Learn (W&L), a framework that converts readily available Internet videos of human computer use into executable UI trajectories at scale.

Match reason: Matches selected tags (Demonstrations).

• Performing IA2 as a priming step before SFT significantly improves the accuracy and calibration of model outputs, as shown by our extensive empirical results on 12 popular benchmarks and two model families.

Match reason: Matches selected tags (Demonstrations).

• In this paper, we introduce LaTeXTrans, a collaborative multi-agent system designed to address this challenge.
• LaTeXTrans ensures format preservation, structural fidelity, and terminology consistency through six specialized agents: 1) a Parser that decomposes LaTeX into translation-friendly units via placeholder substitution and syntax filtering; 2)…

Match reason: Matches selected tags (Demonstrations).

Match reason: Matches selected tags (Demonstrations).

• RA functions in AIL are typically derived from divergence minimization objectives, relying heavily on human design and ingenuity.
• Remarkably, DAIL generalises across unseen environments and policy optimization algorithms, outperforming the current state-of-the-art of \emph{human-designed} baselines.

Match reason: Matches selected tags (Demonstrations).

• Inspired by cognitive science, specifically schema theory, which holds that humans interpret new information by activating pre-existing mental frameworks (schemas) to structure understanding, we introduce Schema-Activated In-Context…
• Schema-Activated In-Context Learning not only bridges disparate ICL strategies ranging from pattern priming to Chain-of-Thought prompting, but also paves a new path for enhancing human-like reasoning in LLMs.

Match reason: Matches selected tags (Demonstrations).

Match reason: Matches selected tags (Demonstrations).

Match reason: Matches selected tags (Demonstrations).

Match reason: Matches selected tags (Demonstrations).

• As a proof-of-concept, we illustrate the use of CausalARC for four language model evaluation settings: (1) abstract reasoning with test-time training, (2) counterfactual reasoning with in-context learning, (3) program synthesis, and (4)…

Match reason: Matches selected tags (Demonstrations).

Match reason: Matches selected tags (Demonstrations).

• We provide 40 ambiguous queries collected from two real-world benchmarks that SIGMOD'26 attendees can use to explore how disambiguation improves SQL generation quality.

Match reason: Matches selected tags (Demonstrations).

• Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions.
• We evaluate with two new benchmarks focused on this capability.

Match reason: Matches selected tags (Demonstrations).

• The model is trained on a dataset of Ubuntu XFCE recordings, which include both randomly generated interactions and realistic interactions produced by AI agents.

Match reason: Matches selected tags (Demonstrations).

Match reason: Matches selected tags (Demonstrations).

Match reason: Matches selected tags (Demonstrations).

• Though execution of instructions in training data remains less reliable than when instructions are given in-context, our results demonstrate that procedural knowledge can be noisily `programmed' into LLMs through PBB, with important…

Match reason: Matches selected tags (Demonstrations).

• We evaluate MOBODY on a wide range of MuJoCo and Adroit benchmarks, demonstrating that it outperforms state-of-the-art off-dynamics RL baselines as well as policy learning methods based on different dynamics learning baselines, with…