DiSP: A Sample-and-Judge Framework for Efficient In-Context Learning Demonstration Selection
DiSP reframes ICL demonstration selection as a prediction problem rather than a search problem, arguing it is cheaper to judge whether a query-context pair will succeed than to find an optimal context. The framework stratifies queries by difficulty using a lightweight router, trains level-specific judges, and applies stop-on-acceptance judging under an explicit budget. Evaluated on five classification datasets with Llama 3-8B and Qwen 2.5-7B, DiSP improves over strong learned selection baselines by up to 3.4% accuracy while achieving up to 23x wall-clock speedup.
Related guides (2)
Related events (8)
ContextRL: Context-aware reinforcement learning improves grounding in agentic and multimodal LLMs
Researchers introduce ContextRL, a reinforcement learning method that trains LLMs to select the context that supports a given query-answer pair from two highly similar candidates, rather than supervising only final answers. The approach constructs contrastive context pairs in two domains: coding agent trajectories (1k pairs) and multimodal image pairs (7k pairs). ContextRL achieves +2.2% average gains over standard GRPO on 5 long-horizon benchmarks and +1.8% across 12 visual QA benchmarks, with ablations showing the gains stem from the context-selection objective rather than the contrastive data alone.
EEVEE: Multi-dataset test-time prompt learning framework for self-improving LLM agents
EEVEE is a new framework enabling LLM agents to perform test-time prompt learning across heterogeneous multi-dataset task streams, addressing a gap where prior methods only handled single-dataset settings. The system uses a router to partition inputs into task clusters and assigns them to suitable prompt configurations, optimized via a router-prompt co-evolution strategy. Experiments show improvements of 10.38 and 24.32 average points over Qwen3-4B-Instruct and DeepSeek-V3.2 respectively, outperforming prior SOTA methods GEPA and ACE by up to 48.2%.
DARP: Semi-parametric retrieval-based imitation learning reduces compounding errors by 15-46%
Researchers introduce DARP (Difference-Aware Retrieval Policies), a semi-parametric imitation learning method that retrieves k-nearest neighbor demonstrations at inference time and predicts actions based on relative distance vectors between neighbor and query states. The approach reparameterizes behavior cloning around local neighborhood structure rather than global state-to-action mappings, requiring no additional data collection or online expert feedback. Across continuous control and robotic manipulation tasks, DARP shows 15-46% performance improvements over standard behavior cloning, including on high-dimensional visual inputs.
SARDI: Self-Augmenting Retrieval for Diffusion Language Models using lookahead tokens
Researchers introduce SARDI, a training-free RAG framework for discrete diffusion language models that repurposes discarded low-confidence tokens during denoising as lookahead signals to guide retrieval before output is finalized. The method is retriever-agnostic and applicable to any reasoning-capable discrete diffusion LM. Evaluated across five multi-hop QA benchmarks, SARDI outperforms training-free diffusion and autoregressive retrieval baselines at up to 8x higher throughput.
Canonical-Context On-Policy Distillation (CCOPD) for Multi-Turn LLM Consistency
This paper identifies 'self-anchored drift' as a key failure mode in multi-turn LLMs: when information is revealed incrementally across turns, models produce unsupported assumptions that distort final answers, even when the total evidence is identical to a single-prompt setting. The authors propose Canonical-Context On-Policy Distillation (CCOPD), which trains a student model on incremental multi-turn conversations to match the output distribution of a frozen teacher conditioned on the full clean prompt. Trained only on math conversations, CCOPD achieves a 32% average relative improvement on multi-turn (RAW-SHARDED) tasks and generalizes zero-shot to five out-of-domain task families while preserving single-prompt performance.
DistIL: Distributional DAgger for RL from Rich Feedback beyond single-bit rewards
A new arXiv preprint introduces DistIL, a distributional variant of the DAgger imitation learning algorithm designed to exploit rich feedback signals (execution traces, tool outputs, expert corrections) rather than the single-bit correctness reward used in standard RLVR. The method uses a forward cross-entropy objective that provides monotonic policy improvement guarantees, unlike reverse KL or Jensen-Shannon divergence objectives used in prior self-distillation approaches. Empirically, DistIL outperforms RLVR and self-distillation baselines on scientific reasoning, coding, and hard math benchmarks.
Cross-lingual in-context learning source language selection challenges fine-tuning assumptions
A new arXiv paper conducts a broad empirical study of cross-lingual transfer in few-shot in-context learning (ICL), spanning seven tasks, six models, and a typologically diverse set of languages. The study finds that conventional heuristics from supervised fine-tuning — such as relying on linguistic similarity or data availability — do not consistently transfer to the ICL regime. The authors also analyze language confusion as a key obstacle in generative cross-lingual ICL and propose alternative heuristics for source language selection.
ADAS: Attention-Discounted Adaptive Sampler improves parallel decoding for masked diffusion language models
Researchers propose ADAS, a training-free reranking rule for masked diffusion language model decoding that addresses token interaction failures in parallel token commitment. The method greedily penalizes candidates that attend strongly to already-selected uncertain positions, using attention weights as soft marginal penalties rather than hard constraints. Evaluated on LLaDA-8B-Base and Dream-7B-Base across GSM8K, MATH500, HumanEval, and MBPP, ADAS improves low-NFE performance by 9–10 percentage points on average when plugged into existing samplers with only 3.1% runtime overhead.