论文库

Coding agents tackle successive tasks on an evolving repository, carrying forward edits and writing memory before the next task is known. Selecting memory for unknown next tasks requires balancing future usefulness against the costs of writing and reading it. The actor must also decide when acting on available memory saves effort as the task unfolds. We introduce Coding-Repository Memory (CoReMem), a cost-internalizing framework that guides memory design and actor adaptation through measured memory value on the next task. Prospective segment valuation compares runs of the next task with and without individual trajectory segments from the same inherited repository state, guiding a compact memory built around anchors: repository locations and executable checks. Actor adaptation estimates on-policy memory value within rollout groups with and without memory, using a reward that prioritizes resolution and penalizes step count in successful runs. Provenance-gated value credit assigns the additional value term to steps identified as using memory-supplied anchors, while every step retains outcome credit. On ChainSWE, CoReMem raises the 27B actor's resolve rate from 21.0% to 25.7%, with 17% fewer steps and 11% fewer total cache-aware tokens, including memory-module calls, relative to the untrained actor model without memory.

We investigate whether and how LLMs encode goals: internal neural representations that precede and guide action, and that are flexible enough to be realized through many different execution paths. We construct a coding setting with multiple sub-tasks that allows us to evaluate goal-seeking behavior and the selection of sub-goals. In this setting, we localize an encoding of the next sub-goal in the outputs of a sparse set of attention heads. The same heads can be used to decode the LM's future actions in natural language (e.g., "I'm checking if a word is a palindrome"). We verify that this encoding is causal for next action and is plastic: transplanting it into a different environment, e.g., another programming language, triggers the same operation realized with a different sequence of tokens. The LM also sustains the encoding throughout the action's execution, which is puzzling because a transformer LM without recurrence cannot carry a state forward for more tokens than it has layers left. We propose that it does not need to. Under a non-recurrent goal-seeking (NRGS) account, the LM frequently re-reads the goal from the task specification, compares it with the progress visible in the growing context, and pursues what remains. We test the predictions of this account with targeted causal interventions.

Multi-robot systems face the challenge of efficiently allocating teams of heterogeneous robots to tasks. The task allocation problem is complicated by collaborative interactions between robots where teams of robots develop emergent capabilities that enable them to complete tasks that would be inefficient or impossible for individual robots. To address these challenges, we present an iterative clustering algorithm for collaborative task allocation in heterogeneous multi-robot systems. This approach partitions the computationally intractable global optimization problem into smaller, tractable subproblems by iteratively forming clusters of robots and tasks, then optimizing assignments within each cluster. By ensuring robots remain clustered with their currently assigned tasks, we guarantee monotonic improvement in overall utility with each iteration. We analyze the convergence of the algorithm and characterize how cluster size constraints determine which suboptimal assignments could trap the algorithm. In simulation, iterative clustering consistently outperforms simulated annealing, and a group-based auction in both computation time and solution quality, and outperforms a hedonic game approach in solution quality.

Paper published at NeurIPS 2026. For data-driven PDE surrogates, generalizing across a wide range of initial conditions and physical coefficients requires a training set of numerical simulations that consistently covers the resulting dynamics. Yet uniform sampling of these configuration parameters can leave challenging regimes insufficiently covered, leading to high prediction errors and large error variance in the trained surrogate. To address this sampling imbalance, we introduce the Online Generative Active Sampling (OGAS), which continuously adapts configuration sampling during surrogate training, as an alternative to classical round-based active learning. As the surrogate learns from a stream of simulation data generated online, OGAS trains a fast diffusion model in parallel to sample configuration parameters conditioned on a training difficulty signal, such as loss or uncertainty. This conditional sampler enables OGAS to parametrize subsequent simulations to generate challenging training data by prioritizing configurations with high difficulty values. We evaluate OGAS on 2D PDEs with distinct challenging dynamics-Kuramoto--Sivashinsky, Navier--Stokes, and Gray--Scott-using multiple surrogate architectures and up to 308 configuration parameters. Across the tested PDEs and architectures, OGAS consistently reduces the 99th-percentile prediction error and overall error dispersion compared with uniform sampling, while wall-clock overhead is negligible. Code and experiments are available at https://github.com/melissa-sa/ogas.

Quantifying disease-associated renal tubular remodeling is challenging because tubular appearances are heterogeneous. We introduce TuMAP (Tubular Morphotype-Aware Pathomics), a pipeline combining (1) dual-view foundation-model representations and provisional morphotype annotation, (2) compositional and within-morphotype pathomics, and (3) patient-level statistical inference. From 456,158 tubules in 358 PAS-stained kidney biopsy slides, TuMAP identified eight image-based morphotypes, seven of which showed stable subsampling assignments. Across 219 patients in six diagnostic groups, diabetic nephropathy (DN) and tubulointerstitial nephritis/acute tubular injury (TIN/ATI) each differed from minimal change disease in seven morphotype proportions, while IgA nephropathy differed in six. DN showed reduced nuclear solidity and increased eccentricity across all eight morphotypes. Area-normalized nuclear density exposed additional within-morphotype differences. TuMAP provides a framework for separating changes in tubular morphotype composition from phenotypic differences within morphotypes.

Multi-agent deep-research systems use delegation to parallelize search and keep long tool traces out of the main agent's context. Yet delegation helps only when task allocation and subtask execution are coordinated: the main agent must issue useful subtasks, while subagents must return reliable evidence. Existing training either optimizes only the main agent or broadcasts the same team advantage to all agents, which can reward misleading subagent reports and penalize useful ones. We introduce LEAD-RL (Learning Effective Agent Delegation with Reinforcement Learning), a joint main-agent-subagent training framework with contribution-aware credit assignment. A training-time rubric evaluates the research utility of each subagent report and gates its inherited team advantage, while final-answer correctness remains the only team reward; no token, step, or speedup reward is used. Across five benchmarks and two model families, LEAD-RL improves answer quality. On BrowseComp, it improves accuracy by 2.49 percentage points and reduces critical-path cost by 24.5% over joint training with shared team credit. During validation, accuracy increases by 6.78 points at approximately constant critical-path cost. These results show that contribution-aware credit assignment improves the quality-efficiency trade-off of multi-agent deep research.